© 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. 1016
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'auditor'

    oai_token-act-pair · gpt-4-turbo

    references to auditoriums

    oai_token-act-pair · gpt-3.5-turbo

    the term "auditor" and related phrases

    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
    uran
    -0.67
    abs
    -0.63
     arrest
    -0.63
     detain
    -0.62
    urtles
    -0.61
    enforcement
    -0.60
    âĵĺ
    -0.60
    theless
    -0.59
    reme
    -0.58
    ering
    -0.57
    POSITIVE LOGITS
     auditor
    1.35
     Auditor
    1.17
    ium
    1.04
    tyard
    0.84
    iosyn
    0.79
    Reviewer
    0.79
    rors
    0.77
    atis
    0.76
    clave
    0.75
    person
    0.74
    Activations Density 0.003%

    No Known Activations