INDEX

Explanations

instances where an action is repeated or done again

oai_token-act-pair · gpt-3.5-turbo

the repetition of the word "once."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

onga

-0.73

RIC

-0.72

aze

-0.70

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.67

 GOODMAN

-0.66

roth

-0.66

olk

-0.66

urga

-0.66

PsyNetMessage

-0.65

NRS

-0.64

POSITIVE LOGITS

 again

0.88

 bitten

0.85

soever

0.80

 Upon

0.79

 mastered

0.72

terday

0.69

 tasted

0.68

 stead

0.66

handedly

0.66

 submar

0.66

Activations Density 0.027%

instances where an action is repeated or done again

the repetition of the word "once."

No Comments

No Known Activations