INDEX

Explanations

specific named entities, potentially related to keyword searches

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific names

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

-0.73

ï¿½ï¿½ï¿½ï¿½

-0.72

 ..."

-0.72

 âĢ¦"

-0.64

[&

-0.64

 laun

-0.63

 constitu

-0.63

geries

-0.62

åĤ

-0.61

)</

-0.61

POSITIVE LOGITS

ogether

0.88

quartered

0.83

sequently

0.81

venants

0.77

vertisements

0.72

mittedly

0.71

 spokesperson

0.71

ward

0.70

tymology

0.70

surprisingly

0.68

Activations Density 0.241%

specific named entities, potentially related to keyword searches

proper nouns and specific names

No Comments

No Known Activations