INDEX

Explanations

prepositions indicating relationships or connections

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the presence of relationships or conditions involving various subjects and 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

,—

-0.73

!,

-0.69

 ancest

-0.69

!.

-0.68

daq

-0.67

,...

-0.67

dit

-0.65

gyn

-0.61

gently

-0.61

olulu

-0.58

POSITIVE LOGITS

 varies

0.66

advertisement

0.64

 matters

0.59

Thor

0.58

comings

0.57

tains

0.57

ãĤ·ãĥ£

0.56

stood

0.55

 these

0.55

afer

0.53

Activations Density 0.322%

prepositions indicating relationships or connections

phrases indicating the presence of relationships or conditions involving various subjects and contexts

No Comments

No Known Activations