© 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. 15042
    Prev
    Next
    INDEX
    Explanations

    phrases related to growth in quantity or size

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" along with numerical references

    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
    killed
    -0.73
    wine
    -0.71
    pin
    -0.67
     %%
    -0.66
    PASS
    -0.62
    0000000000000000
    -0.62
     ens
    -0.61
    =""
    -0.59
     principals
    -0.59
    HAEL
    -0.59
    POSITIVE LOGITS
     spite
    1.17
     accordance
    1.10
    efficiency
    1.10
    versely
    1.09
     tandem
    1.07
    roads
    1.05
    clusions
    1.04
     anticipation
    1.04
    versions
    1.02
     lieu
    0.99
    Activations Density 0.186%

    No Known Activations