© 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
    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. 7765
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or something being noticed

    oai_token-act-pair · gpt-3.5-turbo

    indicative verbs that suggest changes or actions occurring

    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
     heels
    -0.65
    verts
    -0.63
    ilst
    -0.63
     Apostles
    -0.63
     chains
    -0.60
     allergy
    -0.60
    igraph
    -0.60
    nels
    -0.58
     contraceptives
    -0.58
    edes
    -0.58
    POSITIVE LOGITS
     happening
    0.93
    ¬¼
    0.83
     done
    0.79
     worth
    0.79
    ritten
    0.78
    aker
    0.74
    needed
    0.73
     Done
    0.73
    pload
    0.72
     missing
    0.72
    Activations Density 0.143%

    No Known Activations