© 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. 1-RES-JB
    11. 20190
    Prev
    Next
    INDEX
    Explanations

    phrases related to staffing, manning, and stocking

    oai_token-act-pair · gpt-3.5-turbo

    terms related to personnel and their management in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    damage
    -0.76
    laughter
    -0.72
    NF
    -0.71
    EVA
    -0.69
    rieved
    -0.68
    Fine
    -0.68
    dam
    -0.66
    adr
    -0.66
    metadata
    -0.63
    Damage
    -0.63
    POSITIVE LOGITS
     manned
    1.16
     staffed
    1.05
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.90
     staffing
    0.88
    ¯¯¯¯¯¯¯¯
    0.78
    emonic
    0.77
    ezvous
    0.71
     vacancies
    0.71
     hel
    0.65
     compet
    0.64
    Activations Density 0.011%

    No Known Activations