INDEX

Explanations

terms related to converting, conversion, or transformed items

oai_token-act-pair · gpt-3.5-turbo

terms related to conversion processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

accompan

-0.78

llah

-0.75

awi

-0.71

 Administration

-0.71

andr

-0.70

ym

-0.65

Mah

-0.65

 Echoes

-0.64

Fram

-0.62

clips

-0.62

POSITIVE LOGITS

ibles

1.08

verted

0.82

itionally

0.79

 into

0.77

itably

0.76

rette

0.75

ible

0.74

itional

0.74

itive

0.72

thouse

0.72

Activations Density 0.040%

terms related to converting, conversion, or transformed items

terms related to conversion processes

No Comments

No Known Activations