© 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. 2-RES-JB
    11. 3988
    Prev
    Next
    INDEX
    Explanations

    numbers related to years

    oai_token-act-pair · gpt-3.5-turbo

    numerical values representing ages or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MO
    -0.60
     srf
    -0.59
    ooks
    -0.58
     Flight
    -0.57
     buildup
    -0.57
     Dri
    -0.56
    ARP
    -0.56
    INS
    -0.55
    orsi
    -0.54
     borderline
    -0.54
    POSITIVE LOGITS
    theless
    1.31
    lihood
    1.09
    ths
    1.00
    een
    0.95
    tons
    0.86
    teen
    0.81
    eenth
    0.79
    hole
    0.76
    terday
    0.75
    ysis
    0.75
    Activations Density 0.021%

    No Known Activations