INDEX

Explanations

phrases related to fulfilling commitments or promises

oai_token-act-pair · gpt-3.5-turbo

phrases related to following through on commitments or obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Fiesta

-0.73

 Mages

-0.66

 Dome

-0.66

 Maced

-0.64

lite

-0.63

 Spells

-0.62

 Jung

-0.62

 Chargers

-0.61

 Grade

-0.60

 Mage

-0.60

POSITIVE LOGITS

rodu

0.77

chers

0.73

ework

0.73

uclear

0.69

arations

0.69

haar

0.68

ays

0.68

0.67

olicy

0.67

apses

0.66

Activations Density 0.174%

phrases related to fulfilling commitments or promises

phrases related to following through on commitments or obligations

No Comments

No Known Activations