INDEX

Explanations

information related to personnel such as doctors, officials, organizers, scientists, and neighbors

oai_token-act-pair · gpt-3.5-turbo

references to medical professionals and officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Posts

-0.70

 Dalai

-0.67

liest

-0.66

âĪĴ

-0.65

 Oval

-0.63

VI

-0.61

cast

-0.60

QL

-0.60

OUT

-0.60

classic

-0.59

POSITIVE LOGITS

 confir

0.84

 encount

0.81

 speculate

0.81

 challeng

0.80

 raided

0.79

 learned

0.79

 ende

0.78

afety

0.77

poons

0.76

 allege

0.75

Activations Density 0.183%

information related to personnel such as doctors, officials, organizers, scientists, and neighbors

references to medical professionals and officials

No Comments

No Known Activations