INDEX

Explanations

phrases related to starting something, like games or events

oai_token-act-pair · gpt-3.5-turbo

words related to starting or initiating actions, particularly in a sports context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

bey

-0.80

odes

-0.76

ugs

-0.73

enegger

-0.69

ortium

-0.68

Feed

-0.66

itsch

-0.66

Scale

-0.63

bent

-0.62

mercial

-0.62

POSITIVE LOGITS

nesota

0.81

pring

0.76

 Occupations

0.71

©¶æ

0.69

 qualifiers

0.68

OURCE

0.68

 inconsistency

0.67

ctory

0.66

RHP

0.66

 pitchers

0.66

Activations Density 0.032%

phrases related to starting something, like games or events

words related to starting or initiating actions, particularly in a sports context

No Comments

No Known Activations