© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone being absent or unavailable

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "out" related to absences or being unavailable

    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
     backgrounds
    -0.63
     Brach
    -0.63
    OPLE
    -0.59
     assemblies
    -0.58
    ULAR
    -0.58
     Emin
    -0.58
     Celestial
    -0.57
    etary
    -0.56
     Liberation
    -0.55
     transitions
    -0.55
    POSITIVE LOGITS
    done
    1.42
    fitted
    1.39
    doing
    1.27
    matched
    1.27
    played
    1.24
    paced
    1.21
    scoring
    1.20
    ranged
    1.19
    stretched
    1.16
    lasting
    1.16
    Activations Density 0.046%

    No Known Activations