INDEX

Explanations

words related to equipment or accessories used outdoors or for physical activities

oai_token-act-pair · gpt-3.5-turbo

specific prefixes or suffixes in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

stellar

-0.73

bable

-0.68

MENT

-0.66

 Trin

-0.64

è£ħ

-0.63

 legion

-0.63

FUL

-0.62

worldly

-0.62

Hero

-0.61

opt

-0.60

POSITIVE LOGITS

ills

0.90

akery

0.89

ogging

0.87

utters

0.87

ickers

0.85

ackers

0.85

ears

0.85

angers

0.84

inches

0.84

ifts

0.84

Activations Density 0.098%

words related to equipment or accessories used outdoors or for physical activities

specific prefixes or suffixes in words

No Comments

No Known Activations