© 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. 8677
    Prev
    Next
    INDEX
    Explanations

    mentions of job titles and company positions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of executive titles or positions in organizations

    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
    zers
    -0.81
    ĺħ
    -0.70
    ources
    -0.68
    uder
    -0.65
     heating
    -0.64
    pson
    -0.63
    fw
    -0.62
     sche
    -0.62
     aggrav
    -0.60
    isSpecialOrderable
    -0.59
    POSITIVE LOGITS
     Sierra
    0.94
     Kap
    0.82
     Kinnikuman
    0.80
     Polaris
    0.78
     Shang
    0.76
     NEC
    0.75
     Deus
    0.74
     Mehran
    0.72
     etc
    0.72
     Lam
    0.71
    Activations Density 0.141%

    No Known Activations