© 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. 11782
    Prev
    Next
    INDEX
    Explanations

    situations where the absence of something important leads to negative consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to dependencies, particularly those pertaining to essential resources and relationships

    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
    WARD
    -0.73
    Minor
    -0.68
     ASA
    -0.66
    nee
    -0.66
    Eastern
    -0.61
    ERG
    -0.61
    KEN
    -0.61
    soDeliveryDate
    -0.61
    Benz
    -0.61
    eln
    -0.59
    POSITIVE LOGITS
     anymore
    1.18
     nor
    1.03
     whatsoever
    0.95
     altogether
    0.90
     slightest
    0.89
     :(
    0.80
     restraints
    0.79
     adequate
    0.79
     protections
    0.75
     markings
    0.74
    Activations Density 0.434%

    No Known Activations