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. 12859
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and documents

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or groups marked by brackets

    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
     Elys
    -0.79
     redu
    -0.69
     deduction
    -0.66
     seiz
    -0.65
     sacrific
    -0.64
     hog
    -0.63
     comprom
    -0.63
     Maced
    -0.62
     cov
    -0.62
     Valhalla
    -0.62
    POSITIVE LOGITS
    sic
    1.55
    ?]
    1.44
    REDACTED
    1.38
    !]
    1.26
    email
    1.24
    insert
    1.23
    â̦]
    1.20
    emphasis
    1.19
    ...]
    1.16
    Pg
    1.13
    Activations Density 0.034%

    No Known Activations