© 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. 7080
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns related to things that are highly successful or have a strong impact

    oai_token-act-pair · gpt-3.5-turbo
    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
    ploma
    -0.70
    plane
    -0.67
    planes
    -0.67
    yg
    -0.66
    loads
    -0.65
    PART
    -0.65
    Hop
    -0.65
    IGH
    -0.64
    ppers
    -0.63
    worthiness
    -0.63
    POSITIVE LOGITS
     altru
    1.09
     deterrent
    0.84
     coping
    0.82
    atives
    0.80
    ative
    0.79
    aneously
    0.77
     contraception
    0.74
     antid
    0.73
     policing
    0.72
    iating
    0.71
    Activations Density 0.088%

    No Known Activations