© 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. 2-RES-JB
    11. 8375
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a state of incompleteness or pending actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something is not confirmed or resolved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    guy
    -0.77
    ahime
    -0.75
    tein
    -0.75
    é¾
    -0.75
    rities
    -0.72
    APTER
    -0.71
    ufact
    -0.70
    VERTISEMENT
    -0.69
    ĪĴ
    -0.67
    sym
    -0.67
    POSITIVE LOGITS
     yet
    0.81
    hin
    0.76
     anymore
    0.71
     Cors
    0.69
    theless
    0.68
     remotely
    0.65
     adequately
    0.63
    abouts
    0.63
     formally
    0.63
    terday
    0.63
    Activations Density 0.017%

    No Known Activations