INDEX

Explanations

references to secrets or secretive elements

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

MigrationBuilder

-0.83

addPreferredGap

-0.78

 становника

-0.78

PyExc

-0.76

timbangkan

-0.71

峙

-0.67

✨:

-0.66

 opgenomen

-0.65

+"/"+

-0.65

digans

-0.64

POSITIVE LOGITS

 secret

2.01

 Secret

1.98

Secret

1.95

 secrets

1.90

 SECRET

1.89

secret

1.87

 Secrets

1.74

secrets

1.59

Secrets

1.58

SECRET

1.54

Activations Density 0.070%

references to secrets or secretive elements

No Comments

No Known Activations