Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 3357
    Prev
    Next
    INDEX
    Explanations

    phrases related to early or initial stages of development or growth

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the early stages of development or emerging entities

    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
    ading
    -0.75
    aded
    -0.72
     cryst
    -0.67
     coded
    -0.63
    ples
    -0.61
     therapists
    -0.60
    ÃŃs
    -0.59
     bindings
    -0.59
     Siber
    -0.59
     paran
    -0.59
    POSITIVE LOGITS
    Enlarge
    0.70
    SEE
    0.66
    gie
    0.65
    RET
    0.64
    YP
    0.64
    STEM
    0.62
     Finch
    0.62
    yssey
    0.61
    ãĤ´ãĥ³
    0.61
    ickr
    0.61
    Activations Density 0.072%

    No Known Activations