INDEX

Explanations

phrases related to something being constantly happening or changing

oai_token-act-pair · gpt-3.5-turbo

phrases indicating repetition or ongoing actions

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

rule

-0.83

hemy

-0.81

inals

-0.69

ramid

-0.69

ENA

-0.68

tein

-0.67

nee

-0.67

hem

-0.66

IDA

-0.66

DF

-0.66

POSITIVE LOGITS

 churn

0.94

 reinvent

0.93

ãĤ£

0.92

motion

0.91

 fluct

0.89

 evolving

0.87

 paced

0.86

 replen

0.84

 spaced

0.83

 monitored

0.82

Activations Density 0.022%

phrases related to something being constantly happening or changing

phrases indicating repetition or ongoing actions

No Comments

No Known Activations