© 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. 4-RES-JB
    11. 9109
    Prev
    Next
    INDEX
    Explanations

    the word "between" along with the following description of a choice or transition between two or more options

    oai_token-act-pair · gpt-3.5-turbo

    phrases about making choices or transitions between different options or states

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

    No Comments

    Negative Logits
    wikipedia
    -0.77
    gow
    -0.76
    brate
    -0.74
    rak
    -0.72
    di
    -0.71
    br
    -0.70
    idth
    -0.70
    vous
    -0.68
    OGR
    -0.68
    tor
    -0.67
    POSITIVE LOGITS
     halves
    0.89
     worlds
    0.76
     sexes
    0.76
     genders
    0.76
     scarce
    0.74
    ãĥīãĥ©ãĤ´ãĥ³
    0.73
     genres
    0.68
     them
    0.68
     seamlessly
    0.68
     hone
    0.67
    Activations Density 0.040%

    No Known Activations