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

    Neuronpedia

    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. 333
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating challenging or negative situations

    oai_token-act-pair · gpt-3.5-turbo

    statements related to failure or inability to succeed

    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
     hots
    -0.66
    haar
    -0.66
     corpus
    -0.66
    eatures
    -0.66
    amiliar
    -0.64
    escription
    -0.63
    Registered
    -0.63
     motif
    -0.62
     pecul
    -0.62
    allery
    -0.62
    POSITIVE LOGITS
     nor
    1.21
    unless
    1.17
     anymore
    1.01
    nor
    0.97
     Especially
    0.94
     :(
    0.93
    laughs
    0.88
    Unless
    0.88
    except
    0.87
    yet
    0.87
    Activations Density 0.540%

    No Known Activations