© 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. 4-RES-JB
    11. 19415
    Prev
    Next
    INDEX
    Explanations

    actions or events related to conclusions and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to actions or events

    oai_token-act-pair · gpt-3.5-turbo
    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
    REF
    -0.76
     UE
    -0.65
     NX
    -0.63
    SOURCE
    -0.62
     Pascal
    -0.60
    ZE
    -0.57
     Canal
    -0.57
    اÙĦ
    -0.56
     Ded
    -0.56
     stewards
    -0.56
    POSITIVE LOGITS
    pace
    1.41
    paces
    1.41
    ettings
    1.31
    creen
    1.31
    mith
    1.30
    hops
    1.24
    hips
    1.24
    hift
    1.22
    uggest
    1.21
    peed
    1.19
    Activations Density 0.444%

    No Known Activations