© 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. 7-RES-JB
    11. 15693
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions of bringing or causing something to happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a transition or movement towards a goal or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NING
    -0.79
    76561
    -0.72
     Wyn
    -0.71
     è£ıè¦ļéĨĴ
    -0.64
    ascript
    -0.63
    ILY
    -0.62
    estyles
    -0.60
    yip
    -0.60
    scl
    -0.59
     dx
    -0.58
    POSITIVE LOGITS
     guiActiveUnfocused
    0.78
    virt
    0.71
    anz
    0.70
    cut
    0.69
    aud
    0.68
    ordinate
    0.67
    hern
    0.66
    coming
    0.64
    GG
    0.62
    ritical
    0.61
    Activations Density 0.216%

    No Known Activations