INDEX

Explanations

phrases related to removal or extraction

oai_token-act-pair · gpt-3.5-turbo

instances of the word "remove" and its variations

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

 msec

-0.74

 Rate

-0.74

 Analy

-0.67

 Dynamics

-0.67

rium

-0.66

zag

-0.65

 Ratings

-0.65

 Winds

-0.64

gio

-0.64

ingham

-0.62

POSITIVE LOGITS

uder

0.82

leted

0.81

 foreskin

0.80

 limbs

0.78

cliffe

0.75

 aback

0.75

utic

0.74

ipp

0.71

 seizures

0.70

oval

0.70

Activations Density 0.033%

phrases related to removal or extraction

instances of the word "remove" and its variations

No Comments

No Known Activations