INDEX

Explanations

phrases related to comparison or addition

oai_token-act-pair · gpt-3.5-turbo

repeated phrases and expressions indicating similarity or comparison

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

 Versus

-0.73

 newsp

-0.65

bp

-0.64

'[

-0.61

Hy

-0.61

 Maintenance

-0.61

 thous

-0.61

 gorilla

-0.60

rarily

-0.60

 Mansion

-0.59

POSITIVE LOGITS

 sidx

0.85

vous

0.75

otton

0.74

 includ

0.72

aturated

0.71

chev

0.70

liga

0.70

este

0.70

 besides

0.69

amples

0.68

Activations Density 0.079%

phrases related to comparison or addition

repeated phrases and expressions indicating similarity or comparison

No Comments

No Known Activations