INDEX

Explanations

terms related to directional movements or locations

oai_token-act-pair · gpt-3.5-turbo

directional terms related to location and movement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ocular

-0.90

obook

-0.77

gdala

-0.75

natureconservancy

-0.73

colo

-0.72

oxide

-0.69

 Guinness

-0.67

coni

-0.66

alogue

-0.65

ĸļ

-0.64

POSITIVE LOGITS

robe

0.98

ward

0.92

ness

0.92

ly

0.87

ments

0.81

wards

0.80

nesses

0.78

enger

0.72

eous

0.72

 Spiral

0.71

Activations Density 0.009%

terms related to directional movements or locations

directional terms related to location and movement

No Comments

No Known Activations