INDEX

Explanations

the word "inn" with different levels of emphasis

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "inn" within words

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

ngth

-0.75

gencies

-0.70

xual

-0.68

ffen

-0.65

¶æ

-0.64

lda

-0.63

ques

-0.63

©¶æ

-0.62

 litter

-0.62

reon

-0.61

POSITIVE LOGITS

ipeg

1.51

ovation

1.20

spir

1.12

ikuman

1.12

osuke

1.01

igan

0.96

ocent

0.94

iband

0.93

ings

0.91

umerable

0.90

Activations Density 0.017%

the word "inn" with different levels of emphasis

occurrences of the substring "inn" within words

No Comments

No Known Activations