© 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. 790
    Prev
    Next
    INDEX
    Explanations

    the word "beginning" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "beginning" or starting points in various contexts

    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
    itsch
    -0.73
    aths
    -0.73
    ategor
    -0.70
    oute
    -0.70
    ules
    -0.70
    oho
    -0.69
    osponsors
    -0.67
    akia
    -0.66
    otton
    -0.65
    adish
    -0.65
    POSITIVE LOGITS
     stages
    0.88
    nings
    0.87
     anew
    0.82
     thereof
    0.81
     phases
    0.74
    EGIN
    0.68
     pains
    0.68
    hesis
    0.65
    owment
    0.64
    ãĤ½
    0.63
    Activations Density 0.025%

    No Known Activations