INDEX

Explanations

verbs related to giving commands or instructions

oai_token-act-pair · gpt-3.5-turbo

instances of commands or directives given by authority figures

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

pmwiki

-0.84

cit

-0.74

ãĤ©

-0.71

tex

-0.69

ãĤ§

-0.69

td

-0.68

burgh

-0.67

Wallet

-0.67

yip

-0.66

bs

-0.66

POSITIVE LOGITS

etary

0.76

 confir

0.73

 deported

0.72

quartered

0.71

uria

0.70

ordering

0.69

 ordering

0.69

 ordered

0.67

lies

0.67

 butcher

0.65

Activations Density 0.021%

verbs related to giving commands or instructions

instances of commands or directives given by authority figures

No Comments

No Known Activations