INDEX

Explanations

references to a specific person or entity named Ald

oai_token-act-pair · gpt-3.5-turbo

references to a specific individual or possibly multiple individuals named Aldous

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

pmwiki

-0.93

 tits

-0.66

 deaf

-0.64

vous

-0.63

 dism

-0.63

awaru

-0.62

 sight

-0.62

uberty

-0.61

ãĥ¥

-0.59

udeau

-0.59

POSITIVE LOGITS

rums

0.96

uin

0.96

ives

0.90

wich

0.87

rum

0.86

0.85

yssey

0.83

onia

0.82

rica

0.82

orf

0.82

Activations Density 0.035%

references to a specific person or entity named Ald

references to a specific individual or possibly multiple individuals named Aldous

No Comments

No Known Activations