© 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. 10-RES-JB
    11. 12893
    Prev
    Next
    INDEX
    Explanations

    words related to a decrease or decline

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andum
    -0.69
    aceous
    -0.62
    aneous
    -0.59
    aneously
    -0.59
    achu
    -0.58
     Kenobi
    -0.57
     Kad
    -0.56
     Pros
    -0.56
    acca
    -0.55
    ificent
    -0.54
    POSITIVE LOGITS
    graded
    1.41
    grading
    1.35
    LOAD
    1.32
    stairs
    1.24
    pour
    1.20
    hill
    1.19
    sized
    1.19
    played
    1.18
    grades
    1.15
    vote
    1.14
    Activations Density 0.045%

    No Known Activations