© 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. 11-RES-JB
    11. 9849
    Prev
    Next
    INDEX
    Explanations

    personal pronouns ('I', 'you', 'they', 'he') with strong emotional or assertive connotations

    oai_token-act-pair · gpt-3.5-turbo

    pronouns, particularly focusing on first and third person plural forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    į
    -0.61
    bold
    -0.60
     Mechdragon
    -0.59
    yles
    -0.58
    İĭ
    -0.56
     Forth
    -0.54
     Bravo
    -0.54
     Reloaded
    -0.54
    quished
    -0.54
     Rak
    -0.54
    POSITIVE LOGITS
    're
    1.05
     hear
    0.82
     arrive
    0.81
     realise
    0.79
     aren
    0.79
     inevitably
    0.79
     least
    0.77
     arise
    0.77
     shouldn
    0.76
     encounter
    0.76
    Activations Density 0.138%

    No Known Activations