INDEX

Explanations

sequences of numbers with a specific pattern

oai_token-act-pair · gpt-3.5-turbo

numeric values, specifically those that correspond to the number 2

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

awaru

-0.87

rolet

-0.79

efully

-0.72

etz

-0.70

otle

-0.68

gerald

-0.67

iership

-0.66

Ik

-0.64

uated

-0.63

lehem

-0.62

POSITIVE LOGITS

nd

1.84

ND

1.04

 thirds

0.98

0.96

0.93

0.91

Â½

0.91

0.90

0.87

Activations Density 0.123%

sequences of numbers with a specific pattern

numeric values, specifically those that correspond to the number 2

No Comments

No Known Activations