INDEX

Explanations

verbs related to storytelling and narration

oai_token-act-pair · gpt-3.5-turbo

references to legal proceedings or criminal activities

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

!".

-0.74

'.

-0.73

".[

-0.73

!.

-0.72

."[

-0.70

".

-0.67

.<

-0.67

.ï¿½

-0.67

.""

-0.67

.(

-0.66

POSITIVE LOGITS

Ĭ±

0.55

©¶æ

0.53

)]

0.52

 initial

0.50

amina

0.48

essor

0.47

 workload

0.47

lid

0.46

otomy

0.46

ensibly

0.45

Activations Density 1.737%

verbs related to storytelling and narration

references to legal proceedings or criminal activities

No Comments

No Known Activations