Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9710
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the letter "A" followed by a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "A" in various contexts

    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
     appointments
    -0.68
     outlets
    -0.66
    oids
    -0.66
     stripes
    -0.65
     engagements
    -0.64
     offenses
    -0.63
     assemblies
    -0.61
     interests
    -0.60
     incomes
    -0.60
     electrodes
    -0.60
    POSITIVE LOGITS
    chieve
    1.33
    ircraft
    1.30
    UTH
    1.27
    erial
    1.25
    uckland
    1.23
    ctors
    1.22
    gency
    1.21
    ctions
    1.15
    pex
    1.10
    ffect
    1.09
    Activations Density 0.108%

    No Known Activations