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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3711
    Prev
    Next
    INDEX
    Explanations

    phrases related to staying updated or informed

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to staying current or maintaining information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barg
    -0.76
     Gaw
    -0.74
    BALL
    -0.65
    furt
    -0.65
    yang
    -0.63
     scapego
    -0.63
    Msg
    -0.61
    LET
    -0.60
    èĢħ
    -0.60
    FAULT
    -0.60
    POSITIVE LOGITS
     footing
    0.89
    dates
    0.77
    ruciating
    0.75
     predec
    0.75
     uninterrupted
    0.71
     appearances
    0.69
     subsequ
    0.67
    rates
    0.66
    lished
    0.66
     readings
    0.65
    Activations Density 0.025%

    No Known Activations