© 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. 0-RES-JB
    11. 4063
    Prev
    Next
    INDEX
    Explanations

    words related to filtering processes or technologies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to filtering processes or mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶ħ
    -0.76
    reck
    -0.73
     Zel
    -0.71
     Ezek
    -0.71
     Lloyd
    -0.71
    armed
    -0.70
     Spart
    -0.70
     Ame
    -0.69
    buquerque
    -0.68
     Aston
    -0.68
    POSITIVE LOGITS
     filter
    3.60
     filters
    3.26
     filtering
    2.96
     Filter
    2.72
    filter
    2.58
     filtered
    2.42
    Filter
    2.15
    fil
    1.33
    Fil
    1.30
     Fil
    1.27
    Activations Density 0.012%

    No Known Activations