INDEX

Explanations

phrases that describe or attribute actions or events

oai_token-act-pair · gpt-3.5-turbo

phrases that begin with "which" indicating descriptions or clarifications

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

Behind

-0.69

athi

-0.69

 Solution

-0.69

nor

-0.67

cup

-0.65

uta

-0.64

STE

-0.64

 VIDEOS

-0.62

Et

-0.62

Bas

-0.62

POSITIVE LOGITS

 comprises

1.05

 consisted

1.04

 culminated

1.04

 culmin

1.03

 lasted

1.02

 consists

1.00

 resulted

0.99

 prompted

0.97

 originated

0.93

 occurred

0.93

Activations Density 0.107%

phrases that describe or attribute actions or events

phrases that begin with "which" indicating descriptions or clarifications

No Comments

No Known Activations