INDEX

Explanations

instances related to demonstrating or showing something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "demonstrate" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

-0.99

lake

-0.79

agues

-0.78

cloth

-0.74

ita

-0.74

catentry

-0.72

inventoryQuantity

-0.71

pool

-0.69

osate

-0.69

lez

-0.69

POSITIVE LOGITS

 feats

0.90

how

0.88

 prowess

0.84

 excellence

0.71

 firsthand

0.71

 displeasure

0.71

 proficiency

0.70

matically

0.70

 feasibility

0.70

manship

0.69

Activations Density 0.053%

instances related to demonstrating or showing something

instances of the word "demonstrate" and its variations

No Comments

No Known Activations