INDEX

Explanations

tools or instruments used for various purposes

oai_token-act-pair · gpt-3.5-turbo

references to "tools" and their applications or implications

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

 Atomic

-0.71

 Alps

-0.71

Pacific

-0.70

ancies

-0.69

 Acid

-0.68

 Silence

-0.68

 Sons

-0.65

oul

-0.65

Hai

-0.64

 Clover

-0.64

POSITIVE LOGITS

tips

0.95

kit

0.91

arian

0.79

eering

0.74

assisted

0.72

nels

0.70

 tool

0.69

 tools

0.69

knife

0.68

illary

0.67

Activations Density 0.081%

tools or instruments used for various purposes

references to "tools" and their applications or implications

No Comments

No Known Activations