© 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. 7-RES-JB
    11. 13600
    Prev
    Next
    INDEX
    Explanations

    phrases indicating notable achievements or impactful events

    oai_token-act-pair · gpt-3.5-turbo

    references to certain nouns and adjectives indicating significant qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entric
    -0.71
    parent
    -0.67
    omorphic
    -0.66
    heed
    -0.65
    obic
    -0.64
    omever
    -0.64
    clusive
    -0.63
    quartered
    -0.63
    arry
    -0.63
    omorph
    -0.62
    POSITIVE LOGITS
     yesterday
    0.93
     last
    0.79
     surprisingly
    0.74
     recently
    0.73
    âĹ¼
    0.69
     earlier
    0.68
     extensively
    0.67
     Thursday
    0.64
     LAST
    0.63
     fateful
    0.63
    Activations Density 0.575%

    No Known Activations