© 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. 2-RES-JB
    11. 977
    Prev
    Next
    INDEX
    Explanations

    the word "Job"

    oai_token-act-pair · gpt-4-turbo

    phrases related to employment, particularly emphasizing the word "Job"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Job" and its variations to highlight topics related to employment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħī
    -0.69
    Ô
    -0.66
     EDITION
    -0.65
     Oo
    -0.65
    66666666
    -0.64
     Taiwanese
    -0.63
     nuns
    -0.63
     amplification
    -0.63
     exponent
    -0.62
    ivid
    -0.60
    POSITIVE LOGITS
     Job
    1.01
    Job
    0.92
    job
    0.90
    seys
    0.89
     Simulator
    0.88
    hov
    0.84
    ession
    0.81
    essions
    0.79
     MPG
    0.77
    onom
    0.76
    Activations Density 0.017%

    No Known Activations