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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 9024
    Prev
    Next
    INDEX
    Explanations

    text containing the concept of backward actions or states

    oai_token-act-pair · gpt-3.5-turbo

    terms related to movement in reverse or backward actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.70
    ndra
    -0.68
     AFP
    -0.67
    cade
    -0.65
     House
    -0.63
     Photographer
    -0.63
     LCS
    -0.63
    onis
    -0.63
     Consulting
    -0.61
     Gle
    -0.59
    POSITIVE LOGITS
     backwards
    4.00
     backward
    4.00
     sideways
    1.54
     forwards
    1.34
     forward
    1.28
     downwards
    1.15
     downward
    1.12
     Forward
    1.11
    Forward
    1.08
     regress
    1.04
    Activations Density 0.014%

    No Known Activations