INDEX

Explanations

references to shooting or gun-related actions

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

theless

-1.02

 Decken

-0.73

 hâte

-0.70

giaan

-0.69

̸

-0.68

 suspendu

-0.62

helves

-0.62

 marginBottom

-0.62

ngth

-0.62

🥺

-0.61

POSITIVE LOGITS

 shot

1.93

 shots

1.91

 shoots

1.85

 shoot

1.77

 Shot

1.75

 SHOT

1.73

 Shots

1.70

Shots

1.68

shot

1.64

Shot

1.63

Activations Density 0.067%

references to shooting or gun-related actions

No Comments

No Known Activations