INDEX

Explanations

mentions of specific names or terms with varied linguistic structures

oai_token-act-pair · gpt-3.5-turbo

proper nouns, especially names and brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

BI

-0.55

¶ħ

-0.53

 CONT

-0.52

semb

-0.51

taboola

-0.51

 CONTR

-0.50

tags

-0.50

ASP

-0.49

 recru

-0.48

POSITIVE LOGITS

unia

0.67

idia

0.67

hess

0.66

veland

0.61

REDACTED

0.60

Ã«

0.58

enges

0.58

ragon

0.57

inces

0.57

ledge

0.56

Activations Density 0.623%

mentions of specific names or terms with varied linguistic structures

proper nouns, especially names and brands

No Comments

No Known Activations