INDEX

Explanations

references to sizes

oai_token-act-pair · gpt-3.5-turbo

references to medium sizes in various contexts

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

 Merch

-0.78

çīĪ

-0.75

atche

-0.72

IGHTS

-0.72

 Masquerade

-0.71

èĥ

-0.70

apons

-0.69

ä½ľ

-0.68

alog

-0.68

ADRA

-0.67

POSITIVE LOGITS

 sized

1.12

weights

1.00

medium

0.89

weight

0.86

ship

0.82

 medium

0.77

ature

0.76

intendent

0.74

haired

0.74

-,

0.71

Activations Density 0.015%

references to sizes

references to medium sizes in various contexts

No Comments

No Known Activations