© 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. 21281
    Prev
    Next
    INDEX
    Explanations

    criticisms or negative comments about various subjects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to criticism and evaluation of artistic works

    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
    ospons
    -0.85
    yip
    -0.75
    assador
    -0.74
    wana
    -0.74
    encers
    -0.73
    irmed
    -0.73
    onds
    -0.73
    achusetts
    -0.72
    ieves
    -0.71
    hest
    -0.71
    POSITIVE LOGITS
     gimm
    1.63
     bland
    1.52
     gimmick
    1.47
     cheesy
    1.41
     filler
    1.41
     stale
    1.39
     clich
    1.38
     lackluster
    1.36
     cliché
    1.36
     boring
    1.35
    Activations Density 0.529%

    No Known Activations