INDEX

Explanations

repetitions of the word "same" indicating similarities or comparisons

oai_token-act-pair · gpt-3.5-turbo

the repetition of the word "same" in various contexts

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

ãĤ´ãĥ³

-0.72

reetings

-0.69

rend

-0.68

verty

-0.68

ãĥĥ

-0.67

olate

-0.66

their

-0.66

pletion

-0.65

AFTA

-0.65

ËĪ

-0.65

POSITIVE LOGITS

 applies

1.30

 thing

1.20

 goes

1.16

 happens

1.05

 principle

0.98

 happened

0.96

 holds

0.96

 reasoning

0.95

 principles

0.94

 logic

0.93

Activations Density 0.042%

repetitions of the word "same" indicating similarities or comparisons

the repetition of the word "same" in various contexts

No Comments

No Known Activations