INDEX

Explanations

details or information about past events

oai_token-act-pair · gpt-3.5-turbo

phrases related to events or occurrences, especially questions about them

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tan

-0.80

ahon

-0.77

inently

-0.71

aple

-0.70

keye

-0.68

athered

-0.68

ordes

-0.68

oglu

-0.67

osi

-0.66

iciency

-0.66

POSITIVE LOGITS

 transpired

1.01

 happened

0.83

 unfolded

0.83

 unfolding

0.83

 yesterday

0.81

 unfold

0.80

 Crimea

0.78

 wrong

0.76

 aboard

0.74

 perpetrated

0.73

Activations Density 0.077%

details or information about past events

phrases related to events or occurrences, especially questions about them

No Comments

No Known Activations