INDEX

Explanations

words related to medical conditions or terms containing "orm"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "form."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 franc

-0.68

holder

-0.62

-0.61

etsk

-0.60

 Syri

-0.60

lder

-0.59

ching

-0.59

????????

-0.58

BLIC

-0.58

 Decker

-0.56

POSITIVE LOGITS

ammu

1.01

0.96

orph

0.93

sg

0.90

sin

0.87

urst

0.87

ouse

0.87

spring

0.84

sa

0.82

airs

0.79

Activations Density 0.085%

words related to medical conditions or terms containing "orm"

variations of the word "form."

No Comments

No Known Activations