© 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. 18775
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a negative assessment or worsening situations

    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
    bern
    -0.72
    eur
    -0.67
    #$
    -0.64
    utm
    -0.63
    elin
    -0.62
    ulating
    -0.62
    landers
    -0.60
    hyde
    -0.60
    zyme
    -0.60
    conservancy
    -0.59
    POSITIVE LOGITS
     yet
    1.23
     still
    1.14
     than
    1.12
    yet
    0.96
    than
    0.94
     Than
    0.88
    Yet
    0.83
    Still
    0.79
     Yet
    0.74
     Still
    0.67
    Activations Density 0.072%

    No Known Activations