© 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. 11-RES-JB
    11. 18758
    Prev
    Next
    INDEX
    Explanations

    words related to rescue or saving actions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with rescue operations and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Franch
    -0.66
     killer
    -0.60
    ICE
    -0.60
    ion
    -0.59
    isance
    -0.59
    ICT
    -0.58
     precinct
    -0.57
    IO
    -0.57
     literature
    -0.57
     Pell
    -0.56
    POSITIVE LOGITS
    thening
    1.29
    ues
    1.24
    uers
    1.22
    then
    1.05
    uay
    1.02
    uer
    1.02
    eteenth
    1.02
    thens
    1.02
    emouth
    0.99
    glers
    0.98
    Activations Density 0.102%

    No Known Activations