© 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. 23278
    Prev
    Next
    INDEX
    Explanations

    verbs followed by "to" indicating a tendency or inclination

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe tendencies 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
    pelling
    -0.60
    zbek
    -0.55
    except
    -0.51
    terday
    -0.51
     Possible
    -0.51
    noon
    -0.50
     Kardash
    -0.49
    yz
    -0.49
     subscript
    -0.49
     Polo
    -0.49
    POSITIVE LOGITS
    rils
    1.28
     toward
    1.19
     towards
    1.14
    entious
    1.13
     to
    0.97
    ril
    0.96
    entimes
    0.83
    ered
    0.81
    erest
    0.78
    ering
    0.77
    Activations Density 0.040%

    No Known Activations