© 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. 23197
    Prev
    Next
    INDEX
    Explanations

    phrases related to being present or actively involved in a situation or location

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "out there" or existing in a certain space or situation

    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
     CJ
    -0.80
     ±
    -0.61
     cups
    -0.59
     Cum
    -0.57
     Kobe
    -0.56
     Honour
    -0.56
     fibers
    -0.54
     Armored
    -0.54
     Abrams
    -0.54
     {:
    -0.53
    POSITIVE LOGITS
    abouts
    1.56
    upon
    0.84
    ntil
    0.76
    Sov
    0.76
    geist
    0.75
    edin
    0.75
    tics
    0.74
     guiActiveUn
    0.73
     fortun
    0.71
    ngth
    0.68
    Activations Density 0.113%

    No Known Activations