© 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. 4-RES-JB
    11. 13089
    Prev
    Next
    INDEX
    Explanations

    terms related to software programming syntax and technical descriptions

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" in various contexts within the text

    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
    inav
    -0.72
     Spur
    -0.63
    pedia
    -0.60
     Critics
    -0.59
    atures
    -0.59
     fundra
    -0.59
    isine
    -0.57
    INTON
    -0.57
     paternity
    -0.56
    osate
    -0.56
    POSITIVE LOGITS
     hereby
    1.01
    senal
    0.99
    cussion
    0.96
    rael
    0.91
     deprecated
    0.91
     derived
    0.91
    omorph
    0.90
     effected
    0.90
    olate
    0.89
    ometric
    0.88
    Activations Density 0.524%

    No Known Activations