INDEX

Explanations

words related to causality and results

oai_token-act-pair · gpt-3.5-turbo

phrases related to causality and outcomes

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

intend

-0.67

sie

-0.67

viron

-0.66

irie

-0.65

 jaws

-0.64

fields

-0.64

abases

-0.63

 needles

-0.62

luaj

-0.61

 strawberries

-0.61

POSITIVE LOGITS

 thereof

0.79

ially

0.76

ICLE

0.74

 testament

0.72

Interstitial

0.70

 solely

0.70

rative

0.69

orian

0.67

rary

0.67

inel

0.66

Activations Density 0.202%

words related to causality and results

phrases related to causality and outcomes

No Comments

No Known Activations