INDEX

Explanations

text related to uncertainty or alternatives

oai_token-act-pair · gpt-3.5-turbo

conditional phrases indicating uncertainty or alternatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

}:

-0.66

peror

-0.66

ãĤ´ãĥ³

-0.65

cffffcc

-0.65

URRENT

-0.64

ãĤ´

-0.64

SIGN

-0.63

Sounds

-0.63

ERAL

-0.61

pmwiki

-0.61

POSITIVE LOGITS

 whether

1.49

not

1.08

 merely

1.02

 otherwise

0.99

if

0.98

 simply

0.97

whether

0.96

nam

0.86

acle

0.85

 else

0.85

Activations Density 0.084%

text related to uncertainty or alternatives

conditional phrases indicating uncertainty or alternatives

No Comments

No Known Activations