INDEX

Explanations

terms related to personal attributes or actions

oai_token-act-pair · gpt-3.5-turbo

concepts related to legacy and interpersonal relationships

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

 Identified

-0.53

¿½

-0.53

Detailed

-0.52

 Residents

-0.52

 Comprehensive

-0.52

 Local

-0.52

ashington

-0.51

Published

-0.51

COMPLE

-0.50

 southeastern

-0.50

POSITIVE LOGITS

!"

0.87

guy

0.84

 fuckin

0.84

?!"

0.84

 âĢ¦"

0.81

!!"

0.79

 kinda

0.79

 gonna

0.79

âĢ¦"

0.79

..."

0.78

Activations Density 1.697%

terms related to personal attributes or actions

concepts related to legacy and interpersonal relationships

No Comments

No Known Activations