© 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. 17414
    Prev
    Next
    INDEX
    Explanations

    social media actions like sharing and emailing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sharing or sending content

    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
     seams
    -0.59
     pse
    -0.59
     wra
    -0.57
     Examination
    -0.53
    quartered
    -0.53
     whistle
    -0.53
     Instruments
    -0.52
     Relic
    -0.51
     Sequ
    -0.50
     Lilith
    -0.50
    POSITIVE LOGITS
    æ©
    0.66
    utherford
    0.62
    rolet
    0.62
    encer
    0.61
    friends
    0.61
    oice
    0.58
    rect
    0.55
    ondo
    0.55
    igion
    0.55
     CrossRef
    0.54
    Activations Density 0.072%

    No Known Activations