© 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. 14074
    Prev
    Next
    INDEX
    Explanations

    action or information related to the act of recording

    oai_token-act-pair · gpt-3.5-turbo

    words related to recording and documentation

    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
    adin
    -0.79
    osi
    -0.72
    osate
    -0.69
     defin
    -0.69
    acio
    -0.68
    hiro
    -0.68
    nir
    -0.67
    egal
    -0.66
    enta
    -0.66
    ggles
    -0.66
    POSITIVE LOGITS
     recordings
    0.84
    recorded
    0.82
     conversations
    0.82
     sessions
    0.81
     audio
    0.80
     recording
    0.79
     tapes
    0.78
     LIVE
    0.75
     footage
    0.74
     taped
    0.73
    Activations Density 0.064%

    No Known Activations