INDEX

Explanations

words related to connections or associations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "link" and its variations

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

sburg

-0.78

otos

-0.69

ZI

-0.68

ORK

-0.67

 Penguins

-0.65

 Nights

-0.64

oured

-0.64

ODUCT

-0.63

ccording

-0.62

»Ĵ

-0.62

POSITIVE LOGITS

edin

0.98

link

0.93

chain

0.91

ages

0.90

 connecting

0.86

 linking

0.86

 link

0.86

 links

0.83

later

0.82

 cables

0.79

Activations Density 0.036%

words related to connections or associations

occurrences of the word "link" and its variations

No Comments

No Known Activations