INDEX

Explanations

words related to locations on the border

oai_token-act-pair · gpt-3.5-turbo

words related to relationships and their dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ORED

-0.68

 record

-0.57

 caution

-0.56

 appropriately

-0.56

 wise

-0.56

PHOTOS

-0.54

UID

-0.53

QUI

-0.53

 trap

-0.52

 allowances

-0.52

POSITIVE LOGITS

mere

1.04

isi

0.91

enz

0.89

gling

0.84

zinski

0.84

sch

0.84

stad

0.83

iminary

0.83

ukong

0.82

enburg

0.82

Activations Density 0.109%

words related to locations on the border

words related to relationships and their dynamics

No Comments

No Known Activations