INDEX

Explanations

mentions of specific names or terms, particularly "Ny" and "Kru"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

eering

-0.96

ably

-0.84

IBLE

-0.80

OPLE

-0.75

ÙĦ

-0.74

TAIN

-0.73

ablishment

-0.71

urdue

-0.70

awaru

-0.68

ãĥ´ãĤ¡

-0.67

POSITIVE LOGITS

Ny

1.13

quist

0.92

ota

0.85

borg

0.83

seys

0.77

rites

0.76

yk

0.74

ody

0.73

Ey

0.73

heter

0.72

Activations Density 0.004%

mentions of specific names or terms, particularly "Ny" and "Kru"

mentions of specific names or entities

No Comments

No Known Activations