© 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. 6-RES-JB
    11. 20337
    Prev
    Next
    INDEX
    Explanations

    instances in the text where something changes or a transition occurs

    oai_token-act-pair · gpt-3.5-turbo

    phrases that transition or pivot the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toe
    -0.76
    ours
    -0.71
    ments
    -0.68
    kamp
    -0.65
    ters
    -0.63
    Street
    -0.62
    undo
    -0.61
    orde
    -0.61
    scription
    -0.61
    single
    -0.61
    POSITIVE LOGITS
     abruptly
    0.75
    ©¶æ
    0.75
     proceeded
    0.74
    »Ĵ
    0.74
     suddenly
    0.71
     sshd
    0.71
    etheless
    0.69
    anski
    0.66
     conclud
    0.66
    oiler
    0.65
    Activations Density 0.046%

    No Known Activations