INDEX

Explanations

phrases indicating news coverage or media responses to events

oai_token-act-pair · gpt-3.5-turbo

repeated instances of the word "the" across various contexts

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

ngth

-0.77

herer

-0.75

thood

-0.73

ĸļ

-0.73

Layer

-0.73

ÃĥÃĤ

-0.72

hei

-0.70

strate

-0.69

usb

-0.68

itte

-0.68

POSITIVE LOGITS

 incident

1.17

 latest

1.17

 latter

1.14

 announcement

1.05

 situation

1.05

 outcome

1.03

 ordeal

1.03

 possibility

1.03

 impending

1.03

 discrepancy

1.01

Activations Density 0.590%

phrases indicating news coverage or media responses to events

repeated instances of the word "the" across various contexts

No Comments

No Known Activations