INDEX

Explanations

phrases related to events and actions happening chronologically

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the sequence of events or actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.–

-0.66

="/

-0.66

 actionGroup

-0.65

ards

-0.64

osphere

-0.63

abal

-0.62

NAS

-0.61

ocracy

-0.61

ether

-0.61

":"/

-0.60

POSITIVE LOGITS

sequently

1.00

later

0.84

ward

0.81

sequent

0.79

Later

0.79

 subsequent

0.78

ometime

0.75

 thereafter

0.75

anwhile

0.73

 later

0.72

Activations Density 0.324%

phrases related to events and actions happening chronologically

phrases indicating the sequence of events or actions

No Comments

No Known Activations