© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6871
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting achievement or completion

    oai_token-act-pair · gpt-3.5-turbo

    instances of having "finally" achieved or accomplished something

    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
    always
    -0.80
     constantly
    -0.77
     never
    -0.71
     omitted
    -0.69
    anwhile
    -0.67
    often
    -0.67
     seldom
    -0.66
     continually
    -0.65
     always
    -0.65
     frequently
    -0.65
    POSITIVE LOGITS
    enough
    0.98
     enough
    0.92
    Enough
    0.85
     grasp
    0.84
     realization
    0.83
     Enough
    0.79
     grips
    0.78
     acknowledgement
    0.78
     adulthood
    0.78
     sanity
    0.77
    Activations Density 0.540%

    No Known Activations