INDEX

Explanations

profession-related terms, particularly focusing on scientists and researchers

oai_token-act-pair · gpt-3.5-turbo

terms related to various scientific professions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

avers

-0.80

inki

-0.79

ilver

-0.74

rams

-0.71

 Pradesh

-0.70

¥ŀ

-0.70

ensing

-0.69

sembly

-0.69

ourcing

-0.68

awks

-0.68

POSITIVE LOGITS

 extraord

1.06

 laureate

0.85

itatively

0.83

ically

0.76

="#

0.74

ufact

0.74

osphere

0.72

OGR

0.72

ãĤ¶

0.71

Psy

0.70

Activations Density 0.207%

profession-related terms, particularly focusing on scientists and researchers

terms related to various scientific professions

No Comments

No Known Activations