INDEX

Explanations

mentions of various professions in text, indicating an interest in job roles or career paths

oai_token-act-pair · gpt-3.5-turbo

terms related to various professions and occupations

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

Negative Logits

Oo

-0.74

 Meier

-0.69

coni

-0.65

 Tripoli

-0.65

 Jamaica

-0.62

MAD

-0.62

 Sudan

-0.62

 Rockets

-0.62

 Cuomo

-0.61

 Mald

-0.60

POSITIVE LOGITS

smanship

0.86

 professions

0.85

 Profession

0.82

Builder

0.79

oreal

0.78

rentices

0.78

ession

0.77

ically

0.76

istry

0.76

 profession

0.75

Activations Density 0.046%

mentions of various professions in text, indicating an interest in job roles or career paths

terms related to various professions and occupations

No Known Activations