© 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. 8-RES-JB
    11. 6139
    Prev
    Next
    INDEX
    Explanations

    phrases related to falling into a certain category or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the concept of falling into traps or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    be
    -0.69
    hunt
    -0.68
     indu
    -0.67
     endors
    -0.66
    toe
    -0.65
    enery
    -0.65
     toured
    -0.62
    iere
    -0.62
    conn
    -0.61
    press
    -0.61
    POSITIVE LOGITS
     obscurity
    0.75
     whichever
    0.74
     Disorder
    0.71
    Seg
    0.70
     submission
    0.69
    Role
    0.68
     limbo
    0.67
     trap
    0.66
     position
    0.66
    olester
    0.66
    Activations Density 0.075%

    No Known Activations