INDEX

Explanations

legal terminology related to court cases and procedural language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

IGEN

-0.61

 Alistair

-0.59

 Regret

-0.57

 meaningfully

-0.57

 Hosted

-0.56

 proactively

-0.55

 SIGNIFIC

-0.55

 egregious

-0.55

 enshr

-0.55

 flipped

-0.55

POSITIVE LOGITS

AndEndTag

0.95

setVerticalGroup

0.75

 '\\;'

0.69

 تانيه

0.67

Jeografia

0.65

 beginnetje

0.65

 linkovi

0.65

 actes

0.65

rrggbb

0.64

RTEX

0.64

Activations Density 2.374%

legal terminology related to court cases and procedural language

No Comments

No Known Activations