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. 10-RES-JB
    6. 9726
    Prev
    Next
    INDEX
    Explanations

    phrases related to future expectations or predictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating expectations or anticipated outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.76
    HD
    -0.71
     imagining
    -0.69
    assed
    -0.68
    Loop
    -0.67
    fram
    -0.66
     Sure
    -0.66
     Replacement
    -0.65
    heit
    -0.65
    checking
    -0.65
    POSITIVE LOGITS
     arrive
    1.35
     announce
    1.20
     emerge
    1.18
     unveil
    1.14
     undergo
    1.14
     reap
    1.13
     be
    1.11
     settle
    1.08
     receive
    1.08
     prevail
    1.07
    Activations Density 0.082%

    No Known Activations