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. 8-RES-JB
    6. 19686
    Prev
    Next
    INDEX
    Explanations

    terms related to product recall

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of recalling or remembering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htar
    -0.89
    glers
    -0.88
    iak
    -0.76
    osphere
    -0.72
    zos
    -0.72
    doms
    -0.70
    \\\\\\\\
    -0.69
    ete
    -0.68
    quart
    -0.68
    swick
    -0.67
    POSITIVE LOGITS
     Recall
    0.84
     recall
    0.79
     recalling
    0.71
    Accessory
    0.70
    itory
    0.70
    remember
    0.69
    ufact
    0.65
    pring
    0.65
     valve
    0.65
     valves
    0.64
    Activations Density 0.036%

    No Known Activations