© 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. 7953
    Prev
    Next
    INDEX
    Explanations

    mentions of successful achievements or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verbs "make" and "made."

    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
    heter
    -0.64
    æ©Ł
    -0.64
     Niet
    -0.61
     WATCHED
    -0.61
    hood
    -0.61
    Fram
    -0.60
    bour
    -0.58
     interpreted
    -0.57
     thinking
    -0.57
     begs
    -0.57
    POSITIVE LOGITS
     landfall
    1.17
     strides
    1.12
    hift
    1.11
     headlines
    1.00
     appearances
    0.91
     waves
    0.85
    emort
    0.80
     cameo
    0.78
     playoffs
    0.73
     history
    0.72
    Activations Density 0.111%

    No Known Activations