© 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. 0-RES-JB
    11. 17028
    Prev
    Next
    INDEX
    Explanations

    mention of families

    oai_token-act-pair · gpt-3.5-turbo

    references to families, particularly in the context of trauma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reflex
    -0.72
     transporter
    -0.72
     Asgard
    -0.70
     record
    -0.67
     Thor
    -0.67
     subconscious
    -0.66
     point
    -0.66
     Ragnarok
    -0.65
     Cue
    -0.65
     jerk
    -0.65
    POSITIVE LOGITS
    ilies
    4.72
    ILY
    1.70
    ilial
    1.61
    ily
    1.33
    iles
    1.30
    istries
    1.24
    ili
    1.16
    ilings
    1.15
    iling
    1.13
    iliary
    1.11
    Activations Density 0.012%

    No Known Activations