INDEX

Explanations

short durations of time or events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "short" 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 @ 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

ILLE

-0.86

Materials

-0.73

GAN

-0.73

iances

-0.71

Always

-0.71

ONSORED

-0.69

âĹ¼

-0.69

Magikarp

-0.68

gans

-0.66

å§«

-0.66

POSITIVE LOGITS

sighted

1.05

sword

0.97

 term

0.96

ener

0.95

lived

0.94

ening

0.94

 stature

0.89

ened

0.87

 bursts

0.81

 stint

0.80

Activations Density 0.017%

short durations of time or events

occurrences of the word "short" in various contexts

No Comments

No Known Activations