INDEX

Explanations

phrases related to sequential actions or events

oai_token-act-pair · gpt-3.5-turbo

phrases associated with animals or animal-related actions

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

interstitial

-0.73

³

-0.70

×ª

-0.68

ersive

-0.67

-0.65

obil

-0.65

 âĶľâĶĢâĶĢ

-0.64

ÙĪ

-0.64

arcer

-0.64

ocumented

-0.63

POSITIVE LOGITS

 incompetence

0.67

 inaction

0.64

 whoever

0.62

 whine

0.61

 bait

0.61

 shove

0.59

quo

0.59

 throttle

0.59

 wink

0.59

 fail

0.58

Activations Density 1.129%

phrases related to sequential actions or events

phrases associated with animals or animal-related actions

No Comments

No Known Activations