INDEX

Explanations

references to technical processes or procedures involving manipulation and experimentation, like building and testing circuits

oai_token-act-pair · gpt-3.5-turbo

activity related to testing or experimentation

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

 Shiite

-0.76

 Hezbollah

-0.72

 Nato

-0.71

 NATO

-0.65

pires

-0.62

zbollah

-0.60

 Nobel

-0.59

 Venezuel

-0.59

-0.58

quartered

-0.58

POSITIVE LOGITS

 haha

0.97

 myself

0.84

nesday

0.81

:)

0.78

 ðŁĻĤ

0.76

;)

0.75

:-)

0.72

lol

0.72

 ðŁĺ

0.71

Awesome

0.70

Activations Density 1.720%

references to technical processes or procedures involving manipulation and experimentation, like building and testing circuits

activity related to testing or experimentation

No Comments

No Known Activations