INDEX

Explanations

the word "whatever" in phrases

oai_token-act-pair · gpt-3.5-turbo

instances of the word "whatever" in 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

enburg

-0.92

enberg

-0.90

ea

-0.87

iard

-0.85

por

-0.81

end

-0.80

ert

-0.77

enthal

-0.75

ades

-0.73

lic

-0.72

POSITIVE LOGITS

 else

1.12

soever

1.12

 happened

0.95

 happens

0.93

 floats

0.91

 semblance

0.87

 sorts

0.86

 transpired

0.83

 kinds

0.83

THING

0.81

Activations Density 0.013%

the word "whatever" in phrases

instances of the word "whatever" in various contexts

No Comments

No Known Activations