INDEX

Explanations

phrases related to causality or influence

oai_token-act-pair · gpt-3.5-turbo

instances of the word "to," indicating a focus on expressions of purpose or intention

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

 contrace

-0.70

 tucked

-0.70

 handled

-0.68

Pixel

-0.67

 geared

-0.67

 toured

-0.67

 todd

-0.66

 cared

-0.65

 headlined

-0.65

 touched

-0.65

POSITIVE LOGITS

icial

0.82

ãĥĨãĤ£

0.73

 extinction

0.70

ãĤ´ãĥ³

0.66

minist

0.66

ãĥĩãĤ£

0.66

ym

0.66

 breakthrough

0.66

obin

0.65

ournal

0.65

Activations Density 0.088%

phrases related to causality or influence

instances of the word "to," indicating a focus on expressions of purpose or intention

No Comments

No Known Activations