INDEX

Explanations

terms related to procedural research methodology and findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

iliki

-0.63

 Pingback

-0.60

########.

-0.58

LabelTagHelper

-0.57

Rujukan

-0.57

ότη

-0.56

trische

-0.56

cheibe

-0.55

lera

-0.55

الإنجليزية

-0.54

POSITIVE LOGITS

 occur

0.81

 erfolgt

0.81

OCCURRED

0.81

 dilakukan

0.80

 avven

0.80

 erfolgen

0.79

 occurred

0.77

 erfolgte

0.75

 occurs

0.75

 done

0.74

Activations Density 0.817%

terms related to procedural research methodology and findings

No Comments

No Known Activations