© 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. 483
    Prev
    Next
    INDEX
    Explanations

    phrases related to the ability to do something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    furt
    -0.76
     Irving
    -0.70
     revision
    -0.69
     rejection
    -0.66
     Strikes
    -0.63
     Cance
    -0.62
     UR
    -0.61
     Likes
    -0.61
     Uri
    -0.58
     IB
    -0.57
    POSITIVE LOGITS
    't
    1.45
    berra
    1.19
    adian
    1.12
     afford
    1.01
    NOT
    0.96
     muster
    0.89
     feas
    0.87
    nery
    0.85
    ieve
    0.85
     be
    0.80
    Activations Density 0.170%

    No Known Activations