INDEX

Explanations

words or phrases indicating diversity or a variety of things

oai_token-act-pair · gpt-3.5-turbo

phrases that describe various types or categories of things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

edia

-0.79

aeper

-0.76

eka

-0.73

ahime

-0.70

orney

-0.68

lite

-0.67

opsis

-0.63

itness

-0.63

instein

-0.63

idas

-0.63

POSITIVE LOGITS

 imaginable

0.90

 kinds

0.85

alities

0.83

 goodies

0.82

 shapes

0.74

 sorts

0.72

 combinations

0.70

 varied

0.69

 conceivable

0.68

 things

0.68

Activations Density 0.029%

words or phrases indicating diversity or a variety of things

phrases that describe various types or categories of things

No Comments

No Known Activations