INDEX

Explanations

occurrences of the word "justice" in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

hing

-0.79

acid

-0.78

hetically

-0.75

ramer

-0.73

Dak

-0.73

ergy

-0.72

igslist

-0.72

spring

-0.71

ula

-0.70

urat

-0.70

POSITIVE LOGITS

justice

0.97

fulness

0.96

FUL

0.81

 justice

0.80

lessness

0.75

 SYSTEM

0.74

cellence

0.72

ĪĴ

0.72

 injustice

0.71

fully

0.71

Activations Density 0.026%

occurrences of the word "justice" in various contexts

No Known Activations