INDEX

Explanations

positive words related to impressing or being impressed

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to impressiveness or being impressed

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

ford

-0.65

©¶æ

-0.65

 amino

-0.64

 saline

-0.63

nown

-0.61

access

-0.60

interrupted

-0.59

 hostage

-0.58

adobe

-0.58

RH

-0.58

POSITIVE LOGITS

ments

1.02

ively

1.00

mented

0.94

ment

0.83

 impressed

0.83

 impress

0.77

uates

0.77

MENTS

0.77

iveness

0.74

iated

0.74

Activations Density 0.033%

positive words related to impressing or being impressed

words and phrases related to impressiveness or being impressed

No Comments

No Known Activations