INDEX

Explanations

mentions of travel or exploration

oai_token-act-pair · gpt-3.5-turbo

words related to dialogue or conversation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Ded

-0.77

 cracked

-0.72

lat

-0.70

Inf

-0.67

Dil

-0.64

 Gener

-0.62

Ram

-0.62

Wid

-0.61

 adam

-0.61

Jet

-0.60

POSITIVE LOGITS

ogue

4.96

ogy

1.23

ogle

1.20

itton

1.08

iferation

1.07

og

1.06

fashion

0.96

ength

0.94

oire

0.92

odge

0.91

Activations Density 0.017%

mentions of travel or exploration

words related to dialogue or conversation

No Comments

No Known Activations