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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6573
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership and authority

    oai_token-act-pair · gpt-3.5-turbo

    language related to political accountability and governance

    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
     Krypt
    -0.70
    yz
    -0.69
    çķ
    -0.68
    ONSORED
    -0.68
     Bolt
    -0.67
    Origin
    -0.67
     neighbour
    -0.66
    Vel
    -0.65
     Bub
    -0.65
    onement
    -0.63
    POSITIVE LOGITS
     salaries
    1.02
     vested
    0.98
     discretion
    0.98
     oversee
    0.97
     themselves
    0.92
     resigned
    0.90
     routinely
    0.84
    cius
    0.83
     desks
    0.83
     overseeing
    0.83
    Activations Density 0.763%

    No Known Activations