INDEX

Explanations

acronyms related to law enforcement or technology

oai_token-act-pair · gpt-3.5-turbo

references to political or governmental entities and organizations

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

glers

-0.96

fulness

-0.65

ting

-0.65

 balloon

-0.65

ãĥĦ

-0.65

chell

-0.64

ymes

-0.63

ãĤ¤ãĥĪ

-0.63

chen

-0.62

quez

-0.62

POSITIVE LOGITS

ategory

0.85

PC

0.84

ORPG

0.82

oreal

0.82

etition

0.80

OTUS

0.79

otle

0.79

ustom

0.77

onduct

0.77

oin

0.76

Activations Density 0.014%

acronyms related to law enforcement or technology

references to political or governmental entities and organizations

No Comments

No Known Activations