INDEX

Explanations

mentions of media outlets

oai_token-act-pair · gpt-3.5-turbo

references to media outlets

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

heed

-0.77

 Defin

-0.67

jri

-0.62

eric

-0.61

ayne

-0.61

 Summers

-0.60

sil

-0.58

birds

-0.57

seq

-0.57

olds

-0.57

POSITIVE LOGITS

 outlets

1.06

 outlet

1.05

swick

0.84

eval

0.76

="#

0.73

izen

0.70

tsy

0.68

lisher

0.67

 ende

0.66

itution

0.65

Activations Density 0.027%

mentions of media outlets

references to media outlets

No Known Activations