© 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. 20077
    Prev
    Next
    INDEX
    Explanations

    phrases related to recording or being recorded

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of recording in various contexts

    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
    adin
    -0.86
    ggles
    -0.82
    osi
    -0.69
    hiro
    -0.69
    htar
    -0.69
    adh
    -0.68
    Ĭ±
    -0.67
    kie
    -0.67
    pour
    -0.66
    acio
    -0.66
    POSITIVE LOGITS
    recorded
    0.94
     recordings
    0.86
     tapes
    0.81
     recording
    0.79
     Recording
    0.76
     audio
    0.76
     recorder
    0.75
     conversations
    0.74
     Tape
    0.72
     sessions
    0.72
    Activations Density 0.052%

    No Known Activations