© 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. 8-RES-JB
    11. 6198
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    alternatives or options in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.63
     FAT
    -0.60
     Fine
    -0.58
    sworth
    -0.57
     (.
    -0.56
     elig
    -0.55
     Surveillance
    -0.55
     sanitation
    -0.55
     Tanz
    -0.53
     HELL
    -0.52
    POSITIVE LOGITS
     hers
    0.75
    orean
    0.73
    ãĥ¼ãĥĨ
    0.73
    chard
    0.68
    rea
    0.67
    nam
    0.67
    advertising
    0.67
     theirs
    0.67
    onian
    0.66
    cheon
    0.65
    Activations Density 0.069%

    No Known Activations