© 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. 8-RES-JB
    11. 3086
    Prev
    Next
    INDEX
    Explanations

    instances of lists or multiple entities connected by ', and' within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    clauses that introduce lists or additional details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orem
    -0.76
    SpaceEngineers
    -0.70
    amus
    -0.69
    taboola
    -0.68
    oba
    -0.66
    obook
    -0.65
    ãĤº
    -0.64
    essee
    -0.63
    mie
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
    POSITIVE LOGITS
     including
    1.77
     namely
    1.64
     Including
    1.41
    including
    1.41
     includ
    1.36
     notably
    1.35
     ranging
    1.32
     viz
    1.09
     particularly
    1.05
     albeit
    1.03
    Activations Density 0.495%

    No Known Activations