© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12260
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "was" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inav
    -0.68
     HAVE
    -0.67
     Statements
    -0.67
    olutions
    -0.66
    Hello
    -0.65
     Puzzles
    -0.64
     IMAGES
    -0.63
     Proced
    -0.63
    ologies
    -0.63
    lag
    -0.63
    POSITIVE LOGITS
     subsequently
    1.52
     eventually
    1.44
     later
    1.40
     promptly
    1.27
     thereafter
    1.20
     renamed
    1.18
     then
    1.14
     nicknamed
    1.11
     rewarded
    1.11
     replaced
    1.10
    Activations Density 0.267%

    No Known Activations