INDEX

Explanations

references to awards or achievements

oai_token-act-pair · gpt-3.5-turbo

references to awards and achievements, particularly in the context of individuals or organizations

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

Dialogue

-0.70

ologically

-0.67

Kag

-0.58

UID

-0.58

xual

-0.58

 tolerate

-0.56

Ku

-0.56

osexual

-0.56

JB

-0.55

 benign

-0.55

POSITIVE LOGITS

ioxide

1.07

 Sachs

0.99

tein

0.88

ppe

0.75

agos

0.74

midt

0.73

haps

0.73

xia

0.71

tes

0.70

antha

0.68

Activations Density 0.217%

references to awards or achievements

references to awards and achievements, particularly in the context of individuals or organizations

No Comments

No Known Activations