© 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. 1-RES-JB
    11. 7450
    Prev
    Next
    INDEX
    Explanations

    the letter 'R' followed by a single-digit numerical value ranging from 1 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter "R" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.81
     CPR
    -0.76
    terson
    -0.75
    lihood
    -0.73
    glers
    -0.71
     Totem
    -0.71
    -+-+
    -0.69
     Contra
    -0.69
     Nieto
    -0.69
     Virtue
    -0.69
    POSITIVE LOGITS
    ansom
    1.21
    ascal
    1.16
    haps
    1.10
    enn
    1.09
    outine
    1.04
    aul
    1.03
    acco
    0.97
    anc
    0.97
    senal
    0.96
    outing
    0.96
    Activations Density 0.033%

    No Known Activations