INDEX

Explanations

references to higher levels, standards, or qualities

oai_token-act-pair · gpt-3.5-turbo

references to higher standards or levels 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 @ 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

bers

-0.66

pty

-0.65

uer

-0.65

Ring

-0.63

Sho

-0.62

ogg

-0.62

oire

-0.60

vous

-0.59

 Canaver

-0.59

icate

-0.59

POSITIVE LOGITS

 than

1.05

than

0.98

 tiers

0.94

 levels

0.89

 earners

0.85

 grades

0.84

 pitched

0.82

 priced

0.81

iating

0.79

 ceilings

0.78

Activations Density 0.027%

references to higher levels, standards, or qualities

references to higher standards or levels in various contexts

No Comments

No Known Activations