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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 6-RES-JB
    6. 12856
    Prev
    Next
    INDEX
    Explanations

    mentions of following or joining actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to events and follow-ups in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maxim
    -0.77
     optim
    -0.71
     lull
    -0.71
    ilt
    -0.70
    insk
    -0.69
    ilts
    -0.66
     deterior
    -0.66
    ient
    -0.65
     simpl
    -0.65
     ruins
    -0.65
    POSITIVE LOGITS
     Previously
    0.80
    ANI
    0.73
     Eleven
    0.71
    omore
    0.70
     Nieto
    0.69
    zona
    0.68
     namely
    0.68
    nine
    0.66
    Hart
    0.65
     Previous
    0.64
    Activations Density 0.454%

    No Known Activations