© 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. 8-RES-JB
    11. 112
    Prev
    Next
    INDEX
    Explanations

    words related to therapy or treatment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to thermal or therapeutic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELS
    -0.83
     Strauss
    -0.68
    ULAR
    -0.66
    elson
    -0.65
    UE
    -0.64
    ³³³³³³³³
    -0.64
    urger
    -0.63
    ERT
    -0.61
     Elk
    -0.60
     Blazers
    -0.60
    POSITIVE LOGITS
    apy
    1.38
    apist
    1.37
    idge
    1.04
    nian
    1.03
    pher
    0.99
    mal
    0.95
    odynamic
    0.95
    odynamics
    0.93
    most
    0.92
    mop
    0.89
    Activations Density 0.039%

    No Known Activations