INDEX

Explanations

phrases referring to different perspectives or opinions

oai_token-act-pair · gpt-3.5-turbo

references to perspectives or viewpoints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 sshd

-0.70

é¾

-0.70

apons

-0.67

anon

-0.66

-0.62

nom

-0.62

sbm

-0.61

Brave

-0.61

 Cipher

-0.61

bid

-0.60

POSITIVE LOGITS

tains

0.76

 differentiation

0.74

 view

0.71

 contention

0.69

 reference

0.68

oland

0.67

 overlap

0.66

 divergence

0.65

 Exile

0.64

reference

0.64

Activations Density 0.049%

phrases referring to different perspectives or opinions

references to perspectives or viewpoints

No Comments

No Known Activations