INDEX

Explanations

detailed information or descriptions

oai_token-act-pair · gpt-3.5-turbo

mentions of "details" in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

âĹ¼

-0.70

azar

-0.63

 Jindal

-0.62

ÃŃs

-0.62

squ

-0.62

opez

-0.62

ces

-0.61

Lah

-0.60

own

-0.60

azed

-0.60

POSITIVE LOGITS

 details

1.23

 detail

1.04

details

1.04

 Details

0.98

 particulars

0.94

 specifics

0.90

Details

0.86

afety

0.86

etter

0.84

 descriptions

0.83

Activations Density 0.020%

detailed information or descriptions

mentions of "details" in the text

No Comments

No Known Activations