INDEX

Explanations

keywords related to political terms and events

oai_token-act-pair · gpt-3.5-turbo

references to exit polls

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

hed

-0.81

elf

-0.79

heet

-0.77

ened

-0.76

hemy

-0.74

eday

-0.73

acebook

-0.73

eta

-0.72

yright

-0.71

illac

-0.70

POSITIVE LOGITS

 spoiler

0.79

 pupil

0.75

 door

0.72

Exit

0.68

 doors

0.67

 Door

0.66

 velocity

0.65

oute

0.64

tainment

0.64

prises

0.63

Activations Density 0.019%

keywords related to political terms and events

references to exit polls

No Comments

No Known Activations