© 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. 3-RES-JB
    11. 12174
    Prev
    Next
    INDEX
    Explanations

    instances of the word "least" indicating a contrasting or comparison context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating minimization or concession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bj
    -0.73
     Brun
    -0.68
    dal
    -0.65
    rend
    -0.65
    gars
    -0.64
    kefeller
    -0.63
    axter
    -0.62
    perate
    -0.61
    clerosis
    -0.60
    rence
    -0.60
    POSITIVE LOGITS
     toler
    0.73
    uner
    0.67
     Polk
    0.64
     squares
    0.63
    Station
    0.62
     judging
    0.61
    een
    0.61
    fair
    0.60
    ĻĤ
    0.60
     partly
    0.60
    Activations Density 0.023%

    No Known Activations