INDEX

Explanations

phrases indicating setting something up or initiating an action

oai_token-act-pair · gpt-3.5-turbo

instances of the word "set" and its various contexts

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

issance

-0.74

æŃ¦

-0.70

aud

-0.63

Sense

-0.62

Jay

-0.59

ancing

-0.59

ãĥĨãĤ£

-0.59

alsa

-0.59

ilee

-0.58

POSITIVE LOGITS

tle

1.13

 forth

1.00

 aside

0.94

abl

0.90

rid

0.82

 sail

0.81

tered

0.80

ters

0.76

tering

0.76

 showc

0.75

Activations Density 0.038%

phrases indicating setting something up or initiating an action

instances of the word "set" and its various contexts

No Comments

No Known Activations