INDEX

Explanations

pairs of organizations or groups that are working together or being investigated together

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "and" in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ettings

-0.81

objects

-0.77

å¦

-0.76

rises

-0.75

imens

-0.73

rings

-0.70

pleasant

-0.70

concept

-0.70

bek

-0.69

ãĥ¼ãĥ

-0.69

POSITIVE LOGITS

 Bureau

0.90

ITS

0.87

 academia

0.85

 Department

0.84

 affiliated

0.83

 allied

0.83

 Ministry

0.81

 others

0.81

 Perkins

0.81

 partners

0.80

Activations Density 0.276%

pairs of organizations or groups that are working together or being investigated together

occurrences of the word "and" in the text

No Comments

No Known Activations