INDEX

Explanations

names of educational institutions and related terms such as years and official sites

oai_token-act-pair · gpt-3.5-turbo

references to educational institutions and their affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ãĥķãĤ©

-0.83

ãĥķãĤ¡

-0.81

ãĥĵ

-0.79

-0.77

awk

-0.70

yout

-0.66

west

-0.66

onia

-0.65

èª

-0.64

ãĥ¼ãĤ¯

-0.64

POSITIVE LOGITS

 consume

0.67

ucer

0.59

ulet

0.56

 hers

0.56

 cutter

0.55

 Destination

0.55

ariat

0.55

 holder

0.54

 targ

0.54

 expend

0.54

Activations Density 0.217%

names of educational institutions and related terms such as years and official sites

references to educational institutions and their affiliations

No Comments

No Known Activations