© 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. 3-RES-JB
    11. 15047
    Prev
    Next
    INDEX
    Explanations

    dates and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a delay or prerequisite condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pour
    -0.80
    Nic
    -0.72
    Maker
    -0.72
    cult
    -0.68
    eny
    -0.68
    aque
    -0.68
    eas
    -0.68
    Nik
    -0.67
    ENG
    -0.67
    NRS
    -0.67
    POSITIVE LOGITS
    terday
    0.77
    soever
    0.69
     AFTER
    0.69
    onement
    0.67
    MENTS
    0.67
     afterward
    0.67
    alde
    0.67
    ithub
    0.67
     kickoff
    0.66
     Til
    0.66
    Activations Density 0.029%

    No Known Activations