INDEX

Explanations

expressions related to digital communication or technical terminology

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific character or symbol

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

©¶æ

-0.68

 Alban

-0.67

 paran

-0.67

 Polk

-0.66

 Virgin

-0.65

 Mobil

-0.65

Hof

-0.64

 vulner

-0.64

 sacrific

-0.63

ramid

-0.62

POSITIVE LOGITS

1.13

ï¸ı

1.10

tal

1.08

sure

0.94

SHIP

0.91

ship

0.91

sand

0.90

dx

0.90

ski

0.90

0.89

Activations Density 0.293%

expressions related to digital communication or technical terminology

occurrences of a specific character or symbol

No Comments

No Known Activations