© 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. 3289
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to separate entities or elements within a group

    oai_token-act-pair · gpt-3.5-turbo

    the word "each" in 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
    stones
    -0.75
     Metatron
    -0.67
    kn
    -0.64
     notwithstanding
    -0.61
    ahime
    -0.60
    haven
    -0.59
    OV
    -0.59
    ename
    -0.59
    worn
    -0.58
    acqu
    -0.58
    POSITIVE LOGITS
     successive
    1.10
     individual
    0.82
    THING
    0.81
     paycheck
    0.80
    ertodd
    0.79
    dimension
    0.77
     succeeding
    0.74
    omore
    0.71
    NetMessage
    0.70
     iteration
    0.70
    Activations Density 0.029%

    No Known Activations