© 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. 4-RES-JB
    11. 5110
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completion or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases and expressions of action

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

    No Comments

    Negative Logits
     Torment
    -0.86
     Detail
    -0.75
     Arri
    -0.74
     Objects
    -0.71
     Violent
    -0.69
     Finished
    -0.67
     Mour
    -0.67
     Persons
    -0.66
     Survivors
    -0.66
     Sett
    -0.65
    POSITIVE LOGITS
     experiment
    0.79
     homework
    0.77
     grunt
    0.72
    pless
    0.70
     bidding
    0.70
    unia
    0.68
     diligence
    0.67
    pez
    0.67
     anecd
    0.66
    cially
    0.66
    Activations Density 0.367%

    No Known Activations