© 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. 4193
    Prev
    Next
    INDEX
    Explanations

    words related to technology, particularly terms with a suffix that could indicate a verb action or a noun object

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "te"

    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
    etheless
    -0.75
     CVE
    -0.71
    IFIED
    -0.66
    DragonMagazine
    -0.64
     demographics
    -0.62
     Timberwolves
    -0.61
     containment
    -0.61
     Hawks
    -0.60
     Corruption
    -0.60
     totality
    -0.60
    POSITIVE LOGITS
    legram
    1.26
    achable
    1.22
    legraph
    1.19
    pee
    1.11
    quila
    1.05
    eming
    1.05
    brate
    0.98
    cn
    0.96
    asers
    0.94
    aching
    0.94
    Activations Density 0.010%

    No Known Activations