INDEX

Explanations

comparisons and contrasts

oai_token-act-pair · gpt-3.5-turbo

phrases related to medical assessments or health conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Its

-0.83

âľ

-0.78

âĢ

-0.75

ãĢ

-0.74

 âľ

-0.72

It

-0.69

âĹı

-0.67

achu

-0.67

Its

-0.66

ðŁ

-0.65

POSITIVE LOGITS

 their

1.38

their

1.25

 THEIR

1.22

 themselves

1.21

 theirs

1.10

 Their

1.00

Their

0.90

selves

0.81

them

0.72

 originals

0.71

Activations Density 1.205%

comparisons and contrasts

phrases related to medical assessments or health conditions

No Comments

No Known Activations