INDEX

Explanations

names, especially those that appear to be misspelled versions of the name "Dave"

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the word "ave" and its variations, indicating a focus on averages or assessments

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

ually

-0.71

TY

-0.68

ION

-0.67

imation

-0.67

ItemThumbnailImage

-0.63

ARGET

-0.63

âĸ¬

-0.63

ion

-0.62

ional

-0.62

SN

-0.61

POSITIVE LOGITS

llan

1.01

astern

0.89

tails

0.78

nesday

0.78

vine

0.75

tta

0.75

tsky

0.74

ornings

0.74

aways

0.74

dit

0.73

Activations Density 0.020%

names, especially those that appear to be misspelled versions of the name "Dave"

the occurrences of the word "ave" and its variations, indicating a focus on averages or assessments

No Comments

No Known Activations