INDEX

Explanations

locations or positions described in relation to an entity

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "next"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kay

-0.80

ische

-0.69

adic

-0.63

lore

-0.62

rosso

-0.62

anners

-0.62

rament

-0.61

adel

-0.60

ampions

-0.59

boys

-0.59

POSITIVE LOGITS

 door

1.17

door

0.82

 Door

0.81

 compr

0.78

 neighbour

0.73

 thereto

0.72

to

0.71

 baseman

0.69

 stairs

0.67

 week

0.66

Activations Density 0.031%

locations or positions described in relation to an entity

occurrences of the word "next"

No Comments

No Known Activations