© 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. 2-RES-JB
    11. 1558
    Prev
    Next
    INDEX
    Explanations

    technical terms related to specifications and science

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specifications and scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anonymity
    -0.75
     blackout
    -0.75
     stiffness
    -0.73
     relaxation
    -0.72
     refunds
    -0.70
     aval
    -0.70
     choking
    -0.69
     rough
    -0.68
     blankets
    -0.66
     heel
    -0.65
    POSITIVE LOGITS
    ific
    1.47
    ification
    1.42
    ified
    1.40
    ifies
    1.34
    imen
    1.31
    ifier
    1.30
    imens
    1.29
    ifications
    1.25
    ifying
    1.21
    ificate
    1.20
    Activations Density 0.020%

    No Known Activations