© 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. 1631
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action, often involving bringing something to a specific state or location

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" and related prepositions

    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
    yles
    -0.70
    NING
    -0.70
     Wyn
    -0.69
     Nir
    -0.65
     è£ıè¦ļéĨĴ
    -0.64
     lever
    -0.62
    ascript
    -0.62
    76561
    -0.60
    ILY
    -0.60
     Apex
    -0.59
    POSITIVE LOGITS
    ritical
    0.73
    anz
    0.70
    virt
    0.68
    eu
    0.67
    ordinate
    0.65
    hern
    0.64
     guiActiveUnfocused
    0.64
    pless
    0.63
    opt
    0.63
    lr
    0.63
    Activations Density 0.298%

    No Known Activations