INDEX

Explanations

verbs related to releasing or causing something powerful or intense

oai_token-act-pair · gpt-3.5-turbo

instances of the word "unleash" 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

 Represent

-0.72

©¶æ

-0.71

aque

-0.71

ental

-0.70

iasis

-0.70

iop

-0.70

ovember

-0.69

sem

-0.68

atem

-0.64

 Advance

-0.64

POSITIVE LOGITS

 havoc

1.00

 unleashed

0.96

 unle

0.87

ãĥ¤

0.82

 mayhem

0.80

 DRAG

0.79

UGE

0.78

 unleash

0.75

ãĤ¸

0.73

doors

0.72

Activations Density 0.032%

verbs related to releasing or causing something powerful or intense

instances of the word "unleash" and its variations

No Comments

No Known Activations