INDEX

Explanations

words related to irritation or annoyance

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "sm" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

•layer 10 - anger

No Comments

Negative Logits

 pleas

-0.68

 Revival

-0.62

EMENT

-0.62

Sym

-0.61

 PowerPoint

-0.60

 monarch

-0.59

 generals

-0.59

uate

-0.58

 Aure

-0.58

 summary

-0.57

POSITIVE LOGITS

oky

1.32

attering

1.30

itten

1.29

udge

1.22

elly

1.14

ugg

1.12

okin

1.12

udging

1.08

iley

1.08

ithing

1.08

Activations Density 0.010%

words related to irritation or annoyance

occurrences of the substring "sm" in various forms

No Comments

No Known Activations