INDEX

Explanations

words related to challenges or difficulties

oai_token-act-pair · gpt-3.5-turbo

references to challenges or difficulties

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

seys

-0.70

ahon

-0.69

miah

-0.67

 Leaves

-0.67

odes

-0.63

reen

-0.63

otide

-0.61

ccording

-0.61

arbon

-0.61

riter

-0.60

POSITIVE LOGITS

 challenge

1.10

enged

1.02

chall

0.96

enges

0.89

Chall

0.88

naires

0.88

 challenges

0.84

 challenging

0.81

ioned

0.81

 challengers

0.78

Activations Density 0.019%

words related to challenges or difficulties

references to challenges or difficulties

No Comments

No Known Activations