© 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. 7021
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of servicing or serving

    oai_token-act-pair · gpt-3.5-turbo

    terms related to service and societal roles

    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
     Consortium
    -0.81
    Reward
    -0.74
    Reader
    -0.72
     Protein
    -0.71
    ingham
    -0.71
    IELD
    -0.70
    HAEL
    -0.68
    RAFT
    -0.67
    UGC
    -0.67
    rastructure
    -0.66
    POSITIVE LOGITS
     serv
    0.96
    vable
    0.91
    ching
    0.87
    ility
    0.86
    teenth
    0.78
    eness
    0.78
    izons
    0.77
    eties
    0.76
    unal
    0.75
    vered
    0.74
    Activations Density 0.013%

    No Known Activations