INDEX

Explanations

phrases related to unexpected or undesired situations in which individuals or groups find themselves

oai_token-act-pair · gpt-3.5-turbo

phrases related to personal experiences and self-reflection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

alez

-0.80

Mub

-0.77

imize

-0.69

pour

-0.67

vert

-0.67

ritz

-0.67

oslov

-0.65

cemic

-0.65

grade

-0.65

 Mehran

-0.63

POSITIVE LOGITS

selves

0.78

 tremend

0.74

peria

0.73

 anew

0.71

CHAT

0.71

æ³

0.68

 personally

0.68

 wanting

0.66

ANS

0.65

 creatively

0.65

Activations Density 0.041%

phrases related to unexpected or undesired situations in which individuals or groups find themselves

phrases related to personal experiences and self-reflection

No Comments

No Known Activations