INDEX

Explanations

instances of the word "ladder," with a preference for occurrences related to physical objects rather than metaphorical ones

oai_token-act-pair · gpt-3.5-turbo

references to ladders and their related concepts

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

null

-0.83

uality

-0.81

 Dragonbound

-0.78

asel

-0.69

fulness

-0.68

iveness

-0.68

 Alic

-0.67

 Consent

-0.67

NULL

-0.67

 Extrem

-0.65

POSITIVE LOGITS

 ladder

1.10

 heights

0.83

pole

0.80

yard

0.78

 scraping

0.76

 pige

0.76

adders

0.76

stairs

0.74

MpServer

0.74

axe

0.74

Activations Density 0.015%

instances of the word "ladder," with a preference for occurrences related to physical objects rather than metaphorical ones

references to ladders and their related concepts

No Comments

No Known Activations