INDEX

Explanations

phrases related to instructions or guidelines

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to communication and understanding

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

escription

-0.69

iversary

-0.68

estern

-0.67

Synopsis

-0.65

aug

-0.64

 Announce

-0.61

 Celebr

-0.59

 teaser

-0.59

 Released

-0.58

iatus

-0.58

POSITIVE LOGITS

 jurisdiction

0.83

 disadvantage

0.82

 limits

0.80

 limitations

0.78

 limit

0.77

 disadvantages

0.75

 impossibility

0.74

 latitude

0.72

 constraints

0.71

 limitation

0.71

Activations Density 1.580%

phrases related to instructions or guidelines

phrases and terms related to communication and understanding

No Comments

No Known Activations