© 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. 2550
    Prev
    Next
    INDEX
    Explanations

    information related to rankings and positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rankings and reviews

    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
    adra
    -0.67
     Rouge
    -0.65
    ifully
    -0.64
     terminating
    -0.61
     endif
    -0.61
     UNCLASSIFIED
    -0.60
    ————————————————
    -0.60
    irez
    -0.59
     waived
    -0.59
    \":
    -0.59
    POSITIVE LOGITS
     rankings
    1.59
     Rankings
    1.42
     metrics
    1.41
     polls
    1.32
     surveys
    1.30
     metric
    1.28
     Nielsen
    1.26
     ratings
    1.24
     survey
    1.23
     census
    1.23
    Activations Density 0.503%

    No Known Activations