INDEX

Explanations

keywords related to technology and product features

oai_token-act-pair · gpt-3.5-turbo

parentheses and other forms of brackets

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

 spir

-0.76

 impeachment

-0.73

ris

-0.73

 electr

-0.71

 contend

-0.70

 spiked

-0.70

 nuts

-0.69

 pale

-0.68

 nitrogen

-0.68

 tear

-0.68

POSITIVE LOGITS

formerly

1.34

...)

1.34

?)

1.31

aka

1.27

sic

1.20

excluding

1.19

including

1.19

optional

1.18

emphasis

1.14

also

1.14

Activations Density 0.185%

keywords related to technology and product features

parentheses and other forms of brackets

No Comments

No Known Activations