INDEX

Explanations

phrases related to comparative analysis or evaluation

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate comparisons or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

quished

-0.89

nin

-0.82

©¶æ¥µ

-0.82

ire

-0.80

plus

-0.79

MIT

-0.78

roo

-0.77

lon

-0.76

icol

-0.76

NES

-0.76

POSITIVE LOGITS

 determining

1.36

 assessing

1.24

 predicting

1.21

 deciding

1.21

 evaluating

1.19

 influencing

1.18

 attracting

1.17

 selecting

1.17

 shaping

1.16

 communicating

1.14

Activations Density 0.134%

phrases related to comparative analysis or evaluation

phrases that indicate comparisons or relationships

No Comments

No Known Activations