INDEX

Explanations

words related to registration and sign-up processes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "register" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

wich

-0.74

ilitarian

-0.69

Ľ

-0.69

adelphia

-0.68

Sax

-0.66

pei

-0.65

yg

-0.65

 Lanka

-0.64

jay

-0.64

Īè

-0.64

POSITIVE LOGITS

ifications

0.89

ifying

0.89

ifiers

0.77

keepers

0.74

essional

0.72

ify

0.72

ifier

0.71

ifiable

0.71

register

0.71

emark

0.71

Activations Density 0.015%

words related to registration and sign-up processes

occurrences of the word "register" and its variants

No Comments

No Known Activations