© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20030
    Prev
    Next
    INDEX
    Explanations

    numerical values mixed with other characters

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers or numeric data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.74
    zie
    -0.67
    .""
    -0.65
    NetMessage
    -0.63
    ãĤ·ãĥ£
    -0.61
    ¥µ
    -0.59
    terday
    -0.59
    hower
    -0.58
    fol
    -0.57
    everal
    -0.56
    POSITIVE LOGITS
     0
    3.03
    0
    1.72
     1
    1.53
     00
    1.31
     01
    1.30
     2
    1.30
     zero
    1.29
     âĪĴ
    1.24
     3
    1.20
     NULL
    1.20
    Activations Density 0.023%

    No Known Activations