© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20895
    Prev
    Next
    INDEX
    Explanations

    verbs related to giving commands or orders

    oai_token-act-pair · gpt-3.5-turbo

    references to control or authority over actions and decisions

    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
    ovember
    -0.84
    itu
    -0.75
    okemon
    -0.71
    ublic
    -0.70
    vest
    -0.69
    enth
    -0.69
    waukee
    -0.69
     Indianapolis
    -0.68
    atform
    -0.67
    fal
    -0.64
    POSITIVE LOGITS
     dictates
    0.99
     dictate
    0.90
     dict
    0.88
     rules
    0.82
     dictated
    0.82
     stip
    0.81
     constraints
    0.81
     limits
    0.80
     forbid
    0.79
    rules
    0.79
    Activations Density 0.081%

    No Known Activations