INDEX

Explanations

comparisons between quantities or characteristics

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" followed by numerical values

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

istries

-0.67

 palate

-0.65

 accordingly

-0.64

wagon

-0.62

advertisement

-0.62

icide

-0.61

icides

-0.61

 convol

-0.60

 ASAP

-0.59

 therein

-0.59

POSITIVE LOGITS

animate

1.01

jured

0.77

clusively

0.76

 accordance

0.76

clus

0.76

cluding

0.76

umerable

0.75

ahime

0.75

achus

0.75

rex

0.75

Activations Density 0.191%

comparisons between quantities or characteristics

occurrences of the word "in" followed by numerical values

No Comments

No Known Activations