INDEX

Explanations

certain characters or character sequences in a text, possibly related to non-standard or encoded information

oai_token-act-pair · gpt-3.5-turbo

repeated occurrences of specific characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ttes

-0.91

dfx

-0.77

atche

-0.74

 Pearce

-0.72

 Wynne

-0.69

olkien

-0.69

 Constantine

-0.68

 Gutenberg

-0.67

 Foss

-0.67

 Lauder

-0.66

POSITIVE LOGITS

¤

1.03

requ

1.03

Ĭ

1.02

Ðº

1.02

Ī

0.97

ļ

0.95

ÑĤ

0.93

¿

0.93

ŀ

0.92

ĭ

0.89

Activations Density 0.008%

certain characters or character sequences in a text, possibly related to non-standard or encoded information

repeated occurrences of specific characters or symbols

No Comments

No Known Activations