© 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. 8-RES-JB
    11. 3122
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Speaker" in a capitalized form

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Speak" or its variations in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.81
     guiActiveUnfocused
    -0.79
    sym
    -0.74
    ORED
    -0.64
     Pradesh
    -0.63
    MpServer
    -0.62
    AMA
    -0.60
    nuts
    -0.60
    wait
    -0.60
     Mercury
    -0.59
    POSITIVE LOGITS
    lling
    1.20
    ciation
    1.19
    eches
    1.08
    culation
    1.05
    cker
    1.03
    igel
    1.03
    aker
    1.02
    edy
    1.01
    eding
    1.00
    akers
    0.99
    Activations Density 0.020%

    No Known Activations