© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23990
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an error has occurred and asks the user to try again later

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "again."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELD
    -0.72
    emet
    -0.71
    plates
    -0.71
    OTT
    -0.70
    emies
    -0.69
    EMP
    -0.68
    Harris
    -0.65
    etus
    -0.65
    Mot
    -0.64
    RIP
    -0.64
    POSITIVE LOGITS
     recycle
    0.77
     intrusive
    0.73
    Cola
    0.68
     escal
    0.67
     unchecked
    0.66
     unsc
    0.66
     login
    0.66
    essage
    0.65
     Scotia
    0.65
    ifying
    0.63
    Activations Density 0.010%

    No Known Activations