INDEX

Explanations

numerical comparisons related to quantities or values

oai_token-act-pair · gpt-3.5-turbo

comparative statistical measurements or trends

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

urai

-0.69

 Unable

-0.66

 blasp

-0.66

 Became

-0.63

 ********************************

-0.63

 âĺ

-0.62

 alias

-0.61

mind

-0.59

Ó

-0.56

CHAT

-0.55

POSITIVE LOGITS

 comparable

1.33

average

1.12

 counterparts

1.12

 predecessors

1.11

 conventional

1.06

 previous

1.02

 equivalents

1.00

 peers

0.98

 normal

0.98

normal

0.98

Activations Density 0.593%

numerical comparisons related to quantities or values

comparative statistical measurements or trends

No Comments

No Known Activations