INDEX

Explanations

people's names

oai_token-act-pair · gpt-3.5-turbo

words that contain specific letter patterns or segments

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

uyomi

-0.74

 ancest

-0.72

mot

-0.71

 thous

-0.69

 commissions

-0.69

 taxp

-0.68

dfx

-0.65

scill

-0.62

 conditional

-0.62

prises

-0.61

POSITIVE LOGITS

STD

0.79

ella

0.71

ierre

0.71

atis

0.70

lain

0.68

oli

0.68

illo

0.67

agne

0.67

 Brand

0.66

illin

0.66

Activations Density 0.245%

people's names

words that contain specific letter patterns or segments

No Comments

No Known Activations