INDEX

Explanations

keywords related to specific companies or products

oai_token-act-pair · gpt-3.5-turbo

mentions of specific platform or company names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 given

-0.68

 particular

-0.64

 unsupported

-0.64

cul

-0.64

 Geral

-0.62

 refrain

-0.62

 washed

-0.62

 particularly

-0.61

 taken

-0.60

 uncertain

-0.60

POSITIVE LOGITS

ifter

0.97

agonist

0.85

EEK

0.84

eeks

0.83

Magikarp

0.81

awk

0.81

atcher

0.81

untu

0.80

ADS

0.80

Games

0.79

Activations Density 0.135%

keywords related to specific companies or products

mentions of specific platform or company names

No Comments

No Known Activations