INDEX

Explanations

mentions or references to live events or shows

oai_token-act-pair · gpt-3.5-turbo

references to live events or broadcasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

OHN

-0.81

xual

-0.78

INTON

-0.77

umbs

-0.70

une

-0.67

 Kirin

-0.67

selage

-0.67

 Shinra

-0.66

 Beir

-0.65

orically

-0.63

POSITIVE LOGITS

lihood

1.27

liest

1.00

lier

1.00

liness

1.00

journal

0.98

 streamed

0.96

Journal

0.94

 streaming

0.94

wire

0.90

blogs

0.88

Activations Density 0.033%

mentions or references to live events or shows

references to live events or broadcasts

No Comments

No Known Activations