INDEX

Explanations

objects or items that can be held or carried

oai_token-act-pair · gpt-3.5-turbo

nouns that refer to various objects or items

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

renheit

-0.76

erenn

-0.76

 Streets

-0.74

»Ĵ

-0.71

ĺ

-0.71

Ļ½

-0.71

Ĳ

-0.70

£ı

-0.70

Phase

-0.68

actionDate

-0.67

POSITIVE LOGITS

 holder

1.35

 wearer

1.23

 worn

1.11

 bearer

1.10

 giveaway

1.08

 holders

1.06

 dangling

1.06

 shaped

1.05

 salesman

1.04

 adorned

1.04

Activations Density 0.329%

objects or items that can be held or carried

nouns that refer to various objects or items

No Comments

No Known Activations