© 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. 13178
    Prev
    Next
    INDEX
    Explanations

    phrases related to being hidden or covered

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" used in various contexts

    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
    NOW
    -0.74
    DL
    -0.74
    llor
    -0.73
    lihood
    -0.71
    UC
    -0.70
    LES
    -0.69
    TIME
    -0.69
    NL
    -0.68
    hai
    -0.68
    URE
    -0.65
    POSITIVE LOGITS
    escap
    1.01
     accordance
    0.95
     lieu
    0.87
     spite
    0.86
     vain
    0.81
     anticipation
    0.80
    clusions
    0.80
     knots
    0.79
    ordinate
    0.77
    clus
    0.76
    Activations Density 0.234%

    No Known Activations