© 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. 11089
    Prev
    Next
    INDEX
    Explanations

    layers or concepts related to stacking or adding elements on top of each other

    oai_token-act-pair · gpt-3.5-turbo

    the word "layer" and its variations

    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
     Predators
    -0.79
    ãĥīãĥ©
    -0.72
    Latin
    -0.72
    ICES
    -0.70
    date
    -0.70
    speaking
    -0.69
    oris
    -0.69
    nia
    -0.68
    photo
    -0.67
    orth
    -0.66
    POSITIVE LOGITS
     layers
    1.42
     layer
    1.36
    layer
    1.14
     Layer
    1.04
    Layer
    1.01
     infiltrate
    0.86
     thickness
    0.84
     layered
    0.84
     coats
    0.78
     veil
    0.77
    Activations Density 0.013%

    No Known Activations