© 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. 3-RES-JB
    11. 13457
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical details, possibly in a list format

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "AND"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nces
    -0.88
    phrine
    -0.80
     externalToEVAOnly
    -0.71
    omorphic
    -0.68
    employment
    -0.67
    mpeg
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
    berus
    -0.65
    ãĤ·ãĥ£
    -0.65
     sidx
    -0.65
    POSITIVE LOGITS
    ARD
    0.86
    INGS
    0.84
    AND
    0.81
    ING
    0.78
    ILL
    0.77
    RAG
    0.74
    AY
    0.74
    ARDS
    0.72
    RY
    0.72
    OGR
    0.72
    Activations Density 0.015%

    No Known Activations