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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12660
    Prev
    Next
    INDEX
    Explanations

    phrases related to museum activities like entertainment, information, preservation, and education

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "The" and similar single-word activations, suggesting a focus on definite articles or specific identifiers

    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
     eleph
    -0.79
     exha
    -0.78
     manif
    -0.78
    nesday
    -0.76
     respons
    -0.74
     prec
    -0.70
     destro
    -0.69
     occas
    -0.69
     compulsory
    -0.68
     solic
    -0.68
    POSITIVE LOGITS
    Posted
    1.19
    WASHINGTON
    1.18
    LOS
    1.12
    Joined
    1.11
    Reviewed
    1.11
    Published
    1.10
    TOR
    1.10
    Latest
    1.09
    SHARE
    1.08
    SAN
    1.07
    Activations Density 0.071%

    No Known Activations