© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 19740
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress or improvements in a particular situation over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating improvement or progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     helicop
    -0.63
     disadvant
    -0.54
    anwhile
    -0.53
     [|
    -0.53
     outwe
    -0.52
    _.
    -0.51
     afterward
    -0.51
    emed
    -0.49
    ß
    -0.49
     Kardash
    -0.49
    POSITIVE LOGITS
    lations
    0.54
     âĢº
    0.49
    yet
    0.47
    rans
    0.47
    olin
    0.46
     Crossref
    0.45
     cryptocurrency
    0.45
    ependent
    0.44
    CRIPTION
    0.44
     Belfast
    0.43
    Activations Density 1.820%

    No Known Activations