© 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. 629
    Prev
    Next
    INDEX
    Explanations

    words ending with the suffix "-ness" or "-ation"

    oai_token-act-pair · gpt-4-turbo

    adjectives and nouns related to mental and emotional states

    oai_token-act-pair · gpt-3.5-turbo

    words related to abstract concepts and social issues

    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
    âĵĺ
    -0.44
    ierra
    -0.41
     redistributed
    -0.39
    dfx
    -0.39
    ulu
    -0.38
    ilan
    -0.37
    elve
    -0.37
    equal
    -0.37
    âĢ²
    -0.36
    OVA
    -0.36
    POSITIVE LOGITS
    terness
    0.59
     Pwr
    0.46
    bender
    0.45
    BACK
    0.43
    natureconservancy
    0.43
    byss
    0.43
    iness
    0.42
     reversal
    0.42
    lessness
    0.42
    etheless
    0.41
    Activations Density 1.598%

    No Known Activations