INDEX

Explanations

words related to actions, decisions, and consequences

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the existence of facts or ongoing states

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

 Manifest

-0.70

 Communities

-0.68

roid

-0.66

styles

-0.65

 Capital

-0.64

 transforms

-0.63

 Unic

-0.63

 Places

-0.62

 Economy

-0.61

 Citiz

-0.61

POSITIVE LOGITS

now

1.09

now

0.91

NOW

0.80

externalActionCode

0.79

 hindsight

0.79

currently

0.76

psey

0.76

raf

0.76

bol

0.74

bn

0.72

Activations Density 1.113%

words related to actions, decisions, and consequences

phrases indicating the existence of facts or ongoing states

No Comments

No Known Activations