© 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. 6940
    Prev
    Next
    INDEX
    Explanations

    words related to desires or expectations

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and expectations regarding actions or behaviors

    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
    Enough
    -0.61
    inelli
    -0.60
     Carney
    -0.58
    ippi
    -0.57
    MK
    -0.56
    olls
    -0.56
    helps
    -0.55
    Wan
    -0.55
    opol
    -0.54
    isen
    -0.54
    POSITIVE LOGITS
     normally
    1.12
     otherwise
    1.10
     expect
    1.08
     ordinarily
    1.07
     prefer
    0.98
     characterize
    0.87
     tolerate
    0.84
     imagine
    0.81
     ideally
    0.81
     encounter
    0.80
    Activations Density 0.086%

    No Known Activations