INDEX

Explanations

mentions of specific names or references to individuals, particularly those associated with legal cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Anſ

-1.06

 Houſe

-1.04

 ſind

-1.04

bibfield

-1.02

 Diſ

-1.01

bibinfo

-0.99

 Reſ

-0.98

ſelves

-0.97

abuena

-0.97

ſelf

-0.97

POSITIVE LOGITS

0.74

 Johnson

0.73

 Smith

0.71

0.69

0.65

0.62

Johnson

0.61

field

0.61

0.59

Activations Density 1.299%

mentions of specific names or references to individuals, particularly those associated with legal cases

No Comments

No Known Activations