© 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. 2-RES-JB
    11. 2053
    Prev
    Next
    INDEX
    Explanations

    phrases related to the beginning or starting point

    oai_token-act-pair · gpt-3.5-turbo

    the word "starting" in various contexts

    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
    itsch
    -1.00
    olly
    -0.77
    ault
    -0.77
    oho
    -0.77
    atu
    -0.76
    Report
    -0.73
    asca
    -0.73
    ortium
    -0.73
    rie
    -0.72
    eely
    -0.72
    POSITIVE LOGITS
    starting
    0.87
     anew
    0.79
    Starting
    0.75
     starting
    0.74
     Starting
    0.74
     pains
    0.68
     salaries
    0.66
     Starts
    0.63
    ablishment
    0.62
    OPLE
    0.62
    Activations Density 0.014%

    No Known Activations