INDEX

Explanations

mentions of various locations or proper nouns

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" used 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

SPA

-0.71

Times

-0.70

,)

-0.66

 Powered

-0.64

FL

-0.63

!)

-0.63

',

-0.63

NVIDIA

-0.62

Tes

-0.62

POSITIVE LOGITS

 thence

1.02

 consequently

0.99

 secondly

0.94

 then

0.87

 hence

0.87

 therefore

0.84

 thus

0.80

 vice

0.78

 thereby

0.78

 possibly

0.77

Activations Density 0.165%

mentions of various locations or proper nouns

the conjunction "and" used in various contexts

No Comments

No Known Activations