© 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. 3889
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to location and tracking

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to law enforcement actions and their implications

    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
    Organ
    -0.73
    Shot
    -0.72
    Crit
    -0.70
    Comb
    -0.67
    Tele
    -0.67
    Silver
    -0.66
    Reports
    -0.65
    Son
    -0.64
    Lic
    -0.63
    Hung
    -0.63
    POSITIVE LOGITS
    vernment
    0.69
    Ħ¢
    0.68
     supra
    0.68
    ĺħ
    0.67
    edom
    0.66
     unemploy
    0.66
    lict
    0.65
    forcement
    0.65
     agre
    0.64
    iazep
    0.64
    Activations Density 0.517%

    No Known Activations