© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 946
    Prev
    Next
    INDEX
    Explanations

    mentions of negatively viewed actions or states

    oai_token-act-pair · gpt-3.5-turbo

    words that are part of descriptive and emotive expressions, particularly adjectives and verbs that convey a strong action or feeling

    oai_token-act-pair · gpt-4-turbo

    descriptors associated with negative attributes or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awar
    -0.51
    {{
    -0.48
    Ö
    -0.45
    cision
    -0.43
    Enlarge
    -0.43
    Reply
    -0.43
    ":[
    -0.41
     Mandatory
    -0.40
    Newsletter
    -0.40
    natureconservancy
    -0.40
    POSITIVE LOGITS
     notwithstanding
    0.58
    ãĥ³ãĤ¸
    0.54
    éĹĺ
    0.52
     preferably
    0.50
     nonetheless
    0.50
     respectively
    0.49
    netflix
    0.48
    =]
    0.46
    ItemThumbnailImage
    0.46
    conservancy
    0.45
    Activations Density 5.995%

    No Known Activations