INDEX

Explanations

phrases indicating comparisons and conditions related to legal or procedural contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ScopeManager

-0.81

"])

-0.75

TagMode

-0.66

"});

-0.66

Hochspringen

-0.65

unknownFields

-0.64

 cherchés

-0.63

 unknownFields

-0.63

 HttpNotFound

-0.62

ActionCreators

-0.61

POSITIVE LOGITS

 like

0.75

like

0.62

 Like

0.59

 Sometimes

0.59

 seperti

0.58

 sometimes

0.58

 zoals

0.57

Like

0.56

 Often

0.53

像

0.53

Activations Density 0.391%

phrases indicating comparisons and conditions related to legal or procedural contexts

No Comments

No Known Activations