Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 12871
    Prev
    Next
    INDEX
    Explanations

    instances where something is unknown or not recognized by the subject

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "know" in various contexts

    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
    ŃĶ
    -0.82
    uilding
    -0.72
    oulos
    -0.71
    attery
    -0.68
    edia
    -0.67
    ccording
    -0.66
    ositories
    -0.65
    Dialogue
    -0.65
    catentry
    -0.65
    assi
    -0.63
    POSITIVE LOGITS
     anymore
    1.02
    ledge
    0.99
     how
    0.83
     nor
    0.80
     anything
    0.79
    ledged
    0.79
    yet
    0.79
     yet
    0.78
     whats
    0.77
     enough
    0.75
    Activations Density 0.103%

    No Known Activations