INDEX

Explanations

unrelated symbols and words, potentially related to coding or errors in text processing

oai_token-act-pair · gpt-3.5-turbo

references to a specific symbol or character representation

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

uay

-0.70

 apes

-0.70

 metic

-0.67

 tremend

-0.66

 misunder

-0.66

bun

-0.66

alien

-0.64

 deed

-0.64

 fragmentation

-0.63

 Zeit

-0.63

POSITIVE LOGITS

âĶĢâĶĢ

1.06

ï¸ı

0.96

âĶĢâĶĢâĶĢâĶĢ

0.88

lean

0.84

uthor

0.82

ternity

0.80

âĵĺ

0.79

null

0.78

âĢł

0.78

athom

0.78

Activations Density 0.236%

unrelated symbols and words, potentially related to coding or errors in text processing

references to a specific symbol or character representation

No Comments

No Known Activations