INDEX

Explanations

mentions of the name "Miral" or similar variations

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the term "Mir" in various contexts

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

OPLE

-0.76

chnology

-0.72

YC

-0.71

ħĭ

-0.70

enegger

-0.66

INESS

-0.65

ļéĨĴ

-0.64

 Combine

-0.63

ential

-0.63

 Tone

-0.62

POSITIVE LOGITS

rors

1.20

acles

1.17

rored

1.16

acle

1.06

ror

1.04

ial

0.96

abella

0.96

amar

0.87

nit

0.86

abilia

0.84

Activations Density 0.014%

mentions of the name "Miral" or similar variations

the occurrences of the term "Mir" in various contexts

No Comments

No Known Activations