© 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. 10-RES-JB
    11. 10776
    Prev
    Next
    INDEX
    Explanations

    instances where something is done individually or in a step-by-step manner

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynt
    -0.74
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.62
    ancies
    -0.61
    BG
    -0.59
     directions
    -0.58
    ').
    -0.57
    Fin
    -0.56
    BALL
    -0.55
    QL
    -0.55
    RG
    -0.55
    POSITIVE LOGITS
    undred
    0.81
    atown
    0.79
    ©¶æ
    0.77
    ousand
    0.76
    elfth
    0.72
     twentieth
    0.70
    yip
    0.69
    ixty
    0.67
    enth
    0.67
    many
    0.67
    Activations Density 0.082%

    No Known Activations