© 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. 7-RES-JB
    11. 22756
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by verbs (especially "to" followed by a verb)

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" in various contexts related to responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.84
    Flags
    -0.75
    sky
    -0.70
    wine
    -0.70
    caps
    -0.69
    grand
    -0.68
    oval
    -0.67
    spir
    -0.67
    olds
    -0.67
    among
    -0.67
    POSITIVE LOGITS
     criticism
    0.84
     requests
    0.82
     request
    0.81
     criticisms
    0.81
     stimuli
    0.76
     variance
    0.75
     challenge
    0.75
     grievances
    0.75
     adversity
    0.74
     resent
    0.73
    Activations Density 0.086%

    No Known Activations