© 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. 7-RES-JB
    11. 13513
    Prev
    Next
    INDEX
    Explanations

    phrases related to directionality, specifically the concept of "upside down" or "upside" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "upside" and related concepts indicating positive potential or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Isle
    -0.90
    nance
    -0.77
    intosh
    -0.74
    naire
    -0.74
    eer
    -0.74
    onne
    -0.73
    ifiable
    -0.73
    ships
    -0.71
    rar
    -0.71
    mr
    -0.69
    POSITIVE LOGITS
    pered
    0.74
    gres
    0.73
    rano
    0.73
    hest
    0.71
    iety
    0.66
    ved
    0.65
    than
    0.65
    acea
    0.65
    lined
    0.65
    sem
    0.64
    Activations Density 0.086%

    No Known Activations