INDEX

Explanations

phrases related to official announcements or documents

oai_token-act-pair · gpt-3.5-turbo

terms related to official documents and press releases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

amping

-0.68

TPPStreamerBot

-0.67

 Solitaire

-0.67

 genomic

-0.61

venge

-0.61

 ILCS

-0.60

 placebo

-0.60

rir

-0.60

 kindred

-0.59

thood

-0.59

POSITIVE LOGITS

 contains

1.49

 reads

1.44

 indicates

1.42

 mentions

1.39

 includes

1.38

 depicts

1.35

 describes

1.32

 specifies

1.30

 suggests

1.26

 alleges

1.24

Activations Density 0.262%

phrases related to official announcements or documents

terms related to official documents and press releases

No Comments

No Known Activations