INDEX

Explanations

names of journalists and news outlets

oai_token-act-pair · gpt-3.5-turbo

mentions of specific journalist names and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ptin

-0.74

PASS

-0.71

odium

-0.66

senal

-0.64

pper

-0.64

pt

-0.64

VIS

-0.61

 discipl

-0.61

BuyableInstoreAndOnline

-0.61

nee

-0.60

POSITIVE LOGITS

 Greenwald

1.18

wald

0.89

 Papers

0.79

vernment

0.77

 Intercept

0.76

ingen

0.74

lishing

0.72

 headlined

0.70

andowski

0.70

iola

0.68

Activations Density 0.008%

names of journalists and news outlets

mentions of specific journalist names and publications

No Comments

No Known Activations