© 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. 9935
    Prev
    Next
    INDEX
    Explanations

    words related to significant changes or reorganizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transformation or restructuring

    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
    erity
    -0.73
     spoilers
    -0.65
     bribes
    -0.64
    gom
    -0.63
     abst
    -0.62
    osity
    -0.60
     hereby
    -0.59
     foul
    -0.59
    iaries
    -0.59
    ously
    -0.58
    POSITIVE LOGITS
    figured
    0.96
    fig
    0.88
    itialized
    0.86
    FORMATION
    0.84
    aping
    0.82
    cend
    0.81
    facing
    0.81
    formation
    0.79
    ital
    0.78
    ension
    0.78
    Activations Density 0.056%

    No Known Activations