© 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. 10-RES-JB
    11. 17381
    Prev
    Next
    INDEX
    Explanations

    numbers and statistical information

    oai_token-act-pair · gpt-3.5-turbo

    financial metrics related to increases and trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apologised
    -0.77
     imperfect
    -0.76
     voic
    -0.76
     flaws
    -0.75
     misunderstand
    -0.75
     disagreed
    -0.75
    forts
    -0.74
     mistrust
    -0.73
     apologise
    -0.73
     despised
    -0.73
    POSITIVE LOGITS
     exponential
    1.28
     tripled
    1.27
     surge
    1.27
     skyrocket
    1.23
     doubling
    1.21
     surging
    1.21
     increase
    1.18
     surges
    1.18
     quadru
    1.18
     soared
    1.17
    Activations Density 0.624%

    No Known Activations