INDEX

Explanations

locations or specific places within sentences

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and sentence endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

avorite

-0.86

tarian

-0.72

istries

-0.69

 glim

-0.66

 caucuses

-0.65

 suspic

-0.65

 newsp

-0.65

 incorrectly

-0.64

ãĥ¼ãĥĨãĤ£

-0.64

 superpower

-0.64

POSITIVE LOGITS

 Regist

0.79

 Levant

0.74

 Amen

0.73

please

0.72

Ã±o

0.72

 lang

0.71

Ney

0.71

 alle

0.70

eds

0.68

lÃ©

0.68

Activations Density 0.199%

locations or specific places within sentences

punctuation marks and sentence endings

No Comments

No Known Activations