© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 15203
    Prev
    Next
    INDEX
    Explanations

    mentions of past events or historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to historical context and trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ity
    -0.75
    plan
    -0.65
     Stuff
    -0.62
     Sahara
    -0.62
    EVA
    -0.62
    Eva
    -0.61
    ysis
    -0.61
    uli
    -0.60
    amins
    -0.59
    ation
    -0.59
    POSITIVE LOGITS
     conduc
    0.85
    orically
    0.78
     oppressed
    0.78
    orical
    0.77
     disadvantaged
    0.77
     incapable
    0.76
     fraught
    0.76
     metic
    0.73
     unreliable
    0.72
    ctr
    0.72
    Activations Density 0.074%

    No Known Activations