INDEX

Explanations

rases related to specific names, titles, or organizations

oai_token-act-pair · gpt-3.5-turbo

specific names, organizations, or entities

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

 PRES

-0.65

 GOODMAN

-0.64

 Rapp

-0.61

 BOOK

-0.58

 interrupt

-0.57

 constitu

-0.56

 Blizz

-0.56

 bestselling

-0.55

 FORM

-0.55

 unlaw

-0.54

POSITIVE LOGITS

sson

0.67

riage

0.63

ortality

0.63

vae

0.61

'/

0.61

 Valhalla

0.60

esis

0.60

isol

0.60

otine

0.58

 Airl

0.58

Activations Density 0.778%

rases related to specific names, titles, or organizations

specific names, organizations, or entities

No Comments

No Known Activations