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. 2-RES-JB
    6. 9567
    Prev
    Next
    INDEX
    Explanations

    instances where something is described as being partially achieved or incomplete, potentially indicating an emphasis on progress or ongoing processes

    oai_token-act-pair · gpt-3.5-turbo

    references to things that are incomplete or not fully realized

    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
    Trend
    -1.08
    eer
    -0.97
    eers
    -0.83
    achu
    -0.78
    iry
    -0.76
     Emin
    -0.74
    ISE
    -0.73
    Reviewer
    -0.72
    alion
    -0.70
    åĤ
    -0.70
    POSITIVE LOGITS
     obscured
    0.89
     exting
    0.88
     overlapping
    0.84
    ©¶æ
    0.82
     blinded
    0.81
     compensated
    0.80
     forgiven
    0.76
     derailed
    0.74
     exempt
    0.74
     cloudy
    0.74
    Activations Density 0.004%

    No Known Activations