INDEX

Explanations

words related to significance or importance

oai_token-act-pair · gpt-3.5-turbo

terms related to scientific classification and terminology

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

beck

-0.62

©¶æ

-0.61

mc

-0.59

Ò

-0.58

bill

-0.58

 largeDownload

-0.58

meal

-0.56

 Roses

-0.56

hod

-0.56

lift

-0.56

POSITIVE LOGITS

ially

1.01

iencies

0.94

ional

0.94

ulty

0.91

ally

0.89

atory

0.89

ance

0.87

inct

0.85

iation

0.84

ula

0.84

Activations Density 0.072%

words related to significance or importance

terms related to scientific classification and terminology

No Comments

No Known Activations