© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 772
    Prev
    Next
    INDEX
    Explanations

    the word 'department'

    oai_token-act-pair · gpt-4-turbo

    references to academic or institutional departments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various departments

    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
    telling
    -0.80
     Rounds
    -0.78
    noon
    -0.68
    moving
    -0.67
     Intent
    -0.64
    piring
    -0.64
    pire
    -0.63
    isers
    -0.63
    guided
    -0.62
     sidx
    -0.62
    POSITIVE LOGITS
     departments
    0.99
    alities
    0.93
    artment
    0.93
    artments
    0.86
     secretaries
    0.85
    ality
    0.84
    ij士
    0.83
     department
    0.83
     manager
    0.80
    al
    0.78
    Activations Density 0.015%

    No Known Activations