Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 9549
    Prev
    Next
    INDEX
    Explanations

    phrases related to habitual actions

    oai_token-act-pair · gpt-3.5-turbo

    references to habits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zac
    -0.75
    cross
    -0.74
     SAR
    -0.72
    ammy
    -0.69
    mberg
    -0.69
    abad
    -0.66
     Mehran
    -0.65
    zona
    -0.63
    ramid
    -0.63
    aucus
    -0.63
    POSITIVE LOGITS
    ually
    1.13
    uated
    1.04
    uate
    1.00
     habits
    0.98
     habit
    0.96
    uation
    0.95
    uates
    0.80
    dayName
    0.79
    ucket
    0.75
    uating
    0.75
    Activations Density 0.016%

    No Known Activations