INDEX

Explanations

conditional statements related to consequences or threats

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Jefus

-0.66

 ſche

-0.65

 ſtate

-0.64

 pleaſure

-0.63

 myſelf

-0.63

 itſelf

-0.62

tanleria

-0.60

̈́

-0.60

évaluateur

-0.59

 houſe

-0.58

POSITIVE LOGITS

 else

0.71

 otherwise

0.61

 altrimenti

0.60

 onCancelled

0.60

perma

0.58

otherwise

0.56

else

0.55

Else

0.55

 sonst

0.54

Otherwise

0.53

Activations Density 0.144%

conditional statements related to consequences or threats

No Comments

No Known Activations