INDEX

Explanations

decimal numbers

oai_token-act-pair · gpt-3.5-turbo

numerical values and measurements

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

 enthusi

-0.70

bun

-0.69

 buggy

-0.67

 traveler

-0.67

 exotic

-0.66

tom

-0.65

 bondage

-0.65

 battered

-0.64

 threatened

-0.64

 valued

-0.63

POSITIVE LOGITS

0.93

0.91

0.90

0.87

0.86

0.85

0.83

Activations Density 0.060%

decimal numbers

numerical values and measurements

No Comments

No Known Activations