INDEX

Explanations

phrases related to news headlines and publications

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "headline" with varying degrees of emphasis

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ajor

-0.80

enhagen

-0.73

rouch

-0.70

ikarp

-0.68

ersen

-0.67

ioch

-0.67

tz

-0.67

gypt

-0.66

sterdam

-0.66

ensis

-0.66

POSITIVE LOGITS

 headline

0.94

 headlines

0.93

ãĥŀ

0.83

 proclaiming

0.80

 Editors

0.77

mast

0.75

 headlined

0.72

lined

0.72

dress

0.70

fig

0.70

Activations Density 0.028%

phrases related to news headlines and publications

occurrences of the word "headline" with varying degrees of emphasis

No Comments

No Known Activations