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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 12831
    Prev
    Next
    INDEX
    Explanations

    HTML formatting tags and web links

    oai_token-act-pair · gpt-3.5-turbo

    HTML tags and structure within the text

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

    No Comments

    Negative Logits
    etheless
    -1.07
    İĭ
    -1.06
    ĵĺ
    -0.88
     exha
    -0.83
    eatures
    -0.82
     satell
    -0.80
     destro
    -0.78
    iversary
    -0.77
    ¥ŀ
    -0.76
     undermin
    -0.74
    POSITIVE LOGITS
    _>
    1.02
    âĸij
    0.91
    TPS
    0.90
    ihad
    0.76
    =>
    0.75
     (<
    0.74
     </
    0.74
    />
    0.73
    board
    0.72
    .</
    0.72
    Activations Density 0.014%

    No Known Activations