© 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. 6-RES-JB
    11. 19736
    Prev
    Next
    INDEX
    Explanations

    specific locations or objects in a text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical locations and contexts in various scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rogens
    -0.68
    someone
    -0.62
    ones
    -0.61
     Serving
    -0.61
     Topic
    -0.60
    pires
    -0.58
    fitting
    -0.57
    racuse
    -0.57
    signed
    -0.57
    Subject
    -0.57
    POSITIVE LOGITS
     spree
    0.85
    eworld
    0.76
     woes
    0.74
     rampage
    0.66
     selves
    0.66
    ãĥķãĤ©
    0.65
    ouf
    0.65
    azeera
    0.64
     respectively
    0.64
    atical
    0.64
    Activations Density 0.285%

    No Known Activations