© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 23753
    Prev
    Next
    INDEX
    Explanations

    statements or phrases indicating a justification or explanation for a situation or action

    oai_token-act-pair · gpt-3.5-turbo

    statements about justification or rationale

    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
    semble
    -0.72
    Interstitial
    -0.66
    chin
    -0.65
     Sour
    -0.65
    inav
    -0.65
     Carbuncle
    -0.64
     Ping
    -0.63
    oba
    -0.62
    agra
    -0.61
     puck
    -0.60
    POSITIVE LOGITS
     why
    0.94
     justifying
    0.86
    abl
    0.85
    forward
    0.77
    why
    0.76
    Origin
    0.74
    pointers
    0.73
     WHY
    0.73
     justify
    0.73
    ="#
    0.71
    Activations Density 0.022%

    No Known Activations