INDEX

Explanations

structured data where comparable values or categories are being compared or listed

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to comparative data or statistics

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

ocracy

-0.72

rog

-0.71

gravity

-0.70

ocrats

-0.69

gery

-0.69

ocratic

-0.68

 Defenders

-0.66

rak

-0.64

enf

-0.64

yers

-0.63

POSITIVE LOGITS

 proport

0.76

 sidx

0.76

çĶ°

0.74

 guiActiveUn

0.72

 thereafter

0.71

ãģĨ

0.71

 sexes

0.70

 situated

0.69

 eleph

0.68

é¾įåĸļå£«

0.67

Activations Density 0.011%

structured data where comparable values or categories are being compared or listed

phrases that refer to comparative data or statistics

No Comments

No Known Activations