© 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. 6823
    Prev
    Next
    INDEX
    Explanations

    instructions or commands requesting a specific action or setting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "specify" and its variations

    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
    ecd
    -0.77
    stra
    -0.72
    vest
    -0.72
    nih
    -0.66
    isol
    -0.66
    utsch
    -0.66
    uses
    -0.66
    luaj
    -0.66
    alog
    -0.65
    assic
    -0.65
    POSITIVE LOGITS
     parameters
    1.02
     thresholds
    1.00
     criteria
    0.97
     deadlines
    0.88
     specifications
    0.87
     rules
    0.84
     wording
    0.81
     distances
    0.81
     beforehand
    0.80
     requirements
    0.80
    Activations Density 0.052%

    No Known Activations