© 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. 4-RES-JB
    11. 7306
    Prev
    Next
    INDEX
    Explanations

    phrases indicating clarification or explanation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "clarify" and its variations

    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
    MET
    -0.75
    pes
    -0.67
    die
    -0.66
    aden
    -0.65
    cgi
    -0.65
    ren
    -0.64
    jay
    -0.63
    @#&
    -0.63
    atri
    -0.63
    ADS
    -0.62
    POSITIVE LOGITS
     clar
    1.08
     clarify
    0.97
     clarified
    0.92
     clarification
    0.90
     wording
    0.85
    ifications
    0.82
    ifying
    0.79
    ifies
    0.79
     deline
    0.75
     misunderstand
    0.72
    Activations Density 0.022%

    No Known Activations