INDEX

Explanations

informative phrases prompting further action or providing details for an audience

oai_token-act-pair · gpt-3.5-turbo

phrases related to obtaining additional information or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aud

-0.64

opped

-0.63

meter

-0.61

 Notting

-0.60

Cro

-0.60

slice

-0.58

Ħ¢

-0.58

geries

-0.57

Output

-0.57

gery

-0.57

POSITIVE LOGITS

 regarding

0.89

natureconservancy

0.85

 info

0.77

 âĩ

0.77

 details

0.76

actionDate

0.73

REG

0.72

":["

0.70

details

0.69

 Reserved

0.69

Activations Density 0.089%

informative phrases prompting further action or providing details for an audience

phrases related to obtaining additional information or resources

No Comments

No Known Activations