© 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. 16477
    Prev
    Next
    INDEX
    Explanations

    phrases related to negation and prohibition

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases and expressions related to motivation or self-worth

    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
     Rhodes
    -0.87
     Tripoli
    -0.78
     Newark
    -0.75
     Robinson
    -0.74
     Hughes
    -0.71
     Discovery
    -0.70
     Liberty
    -0.70
     Nelson
    -0.70
     Gad
    -0.70
     Lyons
    -0.69
    POSITIVE LOGITS
    âĢ
    1.67
    âĿ
    1.19
    âĸł
    1.16
     âĢ
    1.15
    âľ
    1.13
    ãħĭãħĭ
    1.10
    ï¸ı
    1.10
    ðŁij
    1.09
     ãĥ
    1.07
    âĸ
    1.07
    Activations Density 0.695%

    No Known Activations