© 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. 7-RES-JB
    11. 6451
    Prev
    Next
    INDEX
    Explanations

    phrases related to reinstating something or bringing it back

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rein" or its variations, indicating a focus on the concept of restoration or re-establishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGH
    -0.75
     Borough
    -0.75
    DragonMagazine
    -0.72
    ertodd
    -0.69
     Emin
    -0.69
     Occupations
    -0.69
     Survivors
    -0.66
    INGS
    -0.65
     thumbnail
    -0.62
     Colleges
    -0.61
    POSITIVE LOGITS
    vention
    1.36
    statement
    1.33
    stall
    1.27
    itial
    1.13
    itialized
    1.02
    forcer
    0.98
    cess
    0.97
    vision
    0.94
    visor
    0.94
    umat
    0.93
    Activations Density 0.019%

    No Known Activations