INDEX

Explanations

words related to age groups, specifically focusing on children aged 5 and under

oai_token-act-pair · gpt-3.5-turbo

references to age groups and family dynamics

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

fax

-0.72

 Citiz

-0.68

ãĤ§

-0.68

Fall

-0.67

ipher

-0.66

atin

-0.66

MAL

-0.64

akin

-0.64

antha

-0.62

rar

-0.61

POSITIVE LOGITS

 microphones

0.67

 extraord

0.61

 fame

0.59

ãĢĤ

0.59

 budgets

0.58

 talents

0.57

 assistants

0.57

.[

0.55

UGE

0.54

 cuisine

0.54

Activations Density 0.528%

words related to age groups, specifically focusing on children aged 5 and under

references to age groups and family dynamics

No Comments

No Known Activations