INDEX

Explanations

studies or reports indicating trends or statistics

oai_token-act-pair · gpt-3.5-turbo

the phrase "that" indicating statements of factual findings or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ãĤ¤ãĥĪ

-0.71

arted

-0.68

atro

-0.68

iciary

-0.67

oses

-0.65

andem

-0.63

ETA

-0.62

ĪĴ

-0.62

Tank

-0.62

ready

-0.61

POSITIVE LOGITS

 although

1.12

 despite

1.00

 whilst

0.86

 there

0.82

"[

0.82

 whereas

0.82

 unsurprisingly

0.81

 while

0.81

 unlike

0.80

 none

0.75

Activations Density 0.182%

studies or reports indicating trends or statistics

the phrase "that" indicating statements of factual findings or conclusions

No Comments

No Known Activations