INDEX

Explanations

texts related to various languages and characters that do not contribute to the meaning in English

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

raints

-0.91

etsk

-0.80

ukong

-0.73

orship

-0.71

icter

-0.69

ensical

-0.69

nesday

-0.69

iflower

-0.68

conservancy

-0.67

orsche

-0.66

POSITIVE LOGITS

´

0.91

¼

0.89

à¸

0.89

ãĥ£

0.88

à¦

0.88

¡

0.88

ÙĬ

0.88

ng

0.88

¬

0.86

Ð

0.86

Activations Density 0.007%

texts related to various languages and characters that do not contribute to the meaning in English

special characters or symbols in the text

No Comments

No Known Activations