INDEX

Explanations

phrases related to notable examples or instances

oai_token-act-pair · gpt-3.5-turbo

phrases indicating status or identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

urches

-0.74

wald

-0.66

hops

-0.63

obal

-0.63

oples

-0.63

orpor

-0.62

iates

-0.62

oun

-0.62

 violates

-0.62

ink

-0.61

POSITIVE LOGITS

 undoubtedly

0.84

ovie

0.78

Reviewer

0.72

Pad

0.71

0.70

 probably

0.67

 doubtless

0.66

\\\\\\\\

0.65

GROUND

0.64

Va

0.64

Activations Density 0.256%

phrases related to notable examples or instances

phrases indicating status or identity

No Comments

No Known Activations