INDEX

Explanations

words related to subjective ratings and evaluations of movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ثيق

-0.62

ThroughAttribute

-0.57

COA

-0.56

 Rossa

-0.53

调试

-0.50

 enregist

-0.50

affaires

-0.49

curious

-0.48

 conjug

-0.48

 indisponible

-0.47

POSITIVE LOGITS

 action

0.96

 Action

0.78

action

0.76

Action

0.72

исленность

0.70

アクション

0.69

FormTagHelper

0.66

 actie

0.66

 ACTION

0.65

 acción

0.65

Activations Density 0.237%

words related to subjective ratings and evaluations of movies

No Comments

No Known Activations