INDEX

Explanations

mentions of fish-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 myſelf

-1.01

 itſelf

-0.96

 poffible

-0.93

 greateſt

-0.90

Bly

-0.89

 universitarios

-0.85

 purpoſe

-0.85

 maxSize

-0.84

 themſelves

-0.83

 Jefus

-0.83

POSITIVE LOGITS

 fish

2.19

 Fish

2.03

 FISH

1.86

Fish

1.81

fish

1.79

FISH

1.59

 fishes

1.56

 Fisch

1.41

 Fishes

1.31

鱼

1.23

Activations Density 0.031%

mentions of fish-related content

No Comments

No Known Activations