INDEX

Explanations

terms related to different categories or types

oai_token-act-pair · gpt-3.5-turbo

terms related to classification and categorization

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

teness

-0.78

isks

-0.72

ãģį

-0.68

iries

-0.68

Ô

-0.67

yrights

-0.65

 appre

-0.64

illin

-0.63

ãģĵ

-0.62

 Citiz

-0.61

POSITIVE LOGITS

 guiActiveUnfocused

0.88

ologies

0.68

 fare

0.67

Standard

0.66

Versions

0.66

 spectrum

0.65

 preferred

0.65

 imaginable

0.64

 thereof

0.64

 prevailing

0.64

Activations Density 0.468%

terms related to different categories or types

terms related to classification and categorization

No Comments

No Known Activations