© 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. 7027
    Prev
    Next
    INDEX
    Explanations

    phrases related to high stakes or critical situations

    oai_token-act-pair · gpt-3.5-turbo

    concerns related to negative situations or threats

    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
    nih
    -0.63
     "$:/
    -0.60
    obbies
    -0.60
     resemb
    -0.58
     dislike
    -0.57
    xual
    -0.56
     sidx
    -0.56
     preferring
    -0.55
    avour
    -0.55
     resemblance
    -0.55
    POSITIVE LOGITS
     nationwide
    0.73
    Updated
    0.70
    Tuesday
    0.69
    Wednesday
    0.69
     Thursday
    0.68
    Thursday
    0.67
     Tuesday
    0.67
    .>>
    0.66
    Monday
    0.66
     Yesterday
    0.66
    Activations Density 0.677%

    No Known Activations