© 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. 6-RES-JB
    11. 12764
    Prev
    Next
    INDEX
    Explanations

    negative connotations or conflicts related to staff members

    oai_token-act-pair · gpt-3.5-turbo

    references to staff and personnel involvement in projects and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö
    -0.73
    BTC
    -0.73
     Glac
    -0.69
    é»Ĵ
    -0.69
    çķ
    -0.69
    adesh
    -0.67
    Mega
    -0.67
     ç¥ŀ
    -0.67
    Õ
    -0.66
    lag
    -0.65
    POSITIVE LOGITS
     supervisors
    1.01
     tasked
    0.99
     desks
    0.86
     salaries
    0.86
     hired
    0.85
    rity
    0.84
     overseeing
    0.84
     instructed
    0.84
     priv
    0.84
     duties
    0.83
    Activations Density 0.806%

    No Known Activations