© 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. 8-RES-JB
    11. 18545
    Prev
    Next
    INDEX
    Explanations

    mentions of personal challenges or obstacles that individuals have faced

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant life events or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )))
    -0.69
    =>
    -0.67
     POS
    -0.64
     Recommend
    -0.62
     DOD
    -0.62
    vector
    -0.61
     Committees
    -0.61
    }}}
    -0.60
    arget
    -0.60
    ))))
    -0.60
    POSITIVE LOGITS
     his
    1.06
     stint
    1.01
     he
    0.98
     autobi
    0.93
     her
    0.89
     upbringing
    0.88
    ventures
    0.86
     tattoos
    0.86
    His
    0.85
     she
    0.84
    Activations Density 1.405%

    No Known Activations