INDEX

Explanations

references to the number "two" or pairs of items

oai_token-act-pair · gpt-3.5-turbo

instances of the word "two."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

atown

-0.84

renheit

-0.79

Ô

-0.77

ovi

-0.75

 Tradable

-0.72

untu

-0.72

fw

-0.72

yz

-0.71

ugu

-0.69

ondon

-0.68

POSITIVE LOGITS

 halves

1.18

 sexes

0.93

fold

0.93

 sides

0.91

 aforementioned

0.86

 Kore

0.86

 thirds

0.82

 main

0.80

 largest

0.79

 finalists

0.79

Activations Density 0.063%

references to the number "two" or pairs of items

instances of the word "two."

No Comments

No Known Activations