Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 239
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'recruit' or its variations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recruitment

    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
     Oo
    -0.74
    burst
    -0.72
    comb
    -0.71
    oeuv
    -0.70
    othe
    -0.68
    burn
    -0.68
    gard
    -0.67
    ienne
    -0.66
     Minute
    -0.65
    plays
    -0.64
    POSITIVE LOGITS
     recruits
    0.86
     recruiting
    0.81
     recruited
    0.76
     recruit
    0.74
     recruitment
    0.72
    glers
    0.70
     talent
    0.68
    sters
    0.68
    ruit
    0.67
    ãĥ¼ãĥĨ
    0.66
    Activations Density 0.039%

    No Known Activations