INDEX

Explanations

mentions of a specific location or position

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "here."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

omore

-0.63

ONSORED

-0.57

 Heights

-0.55

Medical

-0.55

 Brach

-0.55

Shape

-0.54

 hygiene

-0.53

ggle

-0.51

catentry

-0.51

cig

-0.51

POSITIVE LOGITS

tics

1.33

abouts

1.32

tical

1.22

tic

1.06

here

0.93

trak

0.77

 newsp

0.69

orer

0.67

acus

0.63

lehem

0.63

Activations Density 0.041%

mentions of a specific location or position

occurrences of the word "here."

No Comments

No Known Activations