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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2875
    Prev
    Next
    INDEX
    Explanations

    references to individuals identified by the name prefix "Ab"

    oai_token-act-pair · gpt-3.5-turbo

    the entity or concept denoted by the word "Ab" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LOS
    -0.89
    cloth
    -0.86
    TAIN
    -0.78
    clud
    -0.78
    sticks
    -0.76
     Dragonbound
    -0.76
    lite
    -0.75
    Rated
    -0.74
     scen
    -0.71
    CL
    -0.68
    POSITIVE LOGITS
     Ab
    3.53
    Ab
    2.43
     ab
    1.72
     AB
    1.65
     Abd
    1.52
     Abs
    1.46
     Rab
    1.31
    ab
    1.27
     Ad
    1.27
     Abram
    1.19
    Activations Density 0.018%

    No Known Activations