© 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. 10-RES-JB
    11. 17380
    Prev
    Next
    INDEX
    Explanations

    phrases related to reputation and characteristics associated with individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases or concepts associated with reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eday
    -1.00
    000000
    -0.84
    00000
    -0.79
    arte
    -0.74
     Izan
    -0.74
     realise
    -0.73
    MRI
    -0.73
    alion
    -0.73
     Norn
    -0.72
    çķ
    -0.72
    POSITIVE LOGITS
     unreliable
    0.98
     lax
    0.97
     prolific
    0.97
     harsh
    0.93
     aggressive
    0.93
     notoriously
    0.92
     outspoken
    0.92
     tough
    0.91
     penchant
    0.91
     dogged
    0.90
    Activations Density 0.287%

    No Known Activations