INDEX

Explanations

information or statements attributed to reliable sources, particularly sources like Wikipedia or police reports

oai_token-act-pair · gpt-3.5-turbo

references to authoritative sources or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

quit

-0.71

abiding

-0.70

btn

-0.69

 mattered

-0.67

obyl

-0.67

atible

-0.64

rontal

-0.63

 unrecogn

-0.63

sov

-0.63

ogging

-0.63

POSITIVE LOGITS

 datas

0.81

pedia

0.74

 insider

0.70

 tracker

0.69

glers

0.66

 lore

0.65

 interviewer

0.64

 docs

0.63

 Documentation

0.63

 synopsis

0.63

Activations Density 0.258%

information or statements attributed to reliable sources, particularly sources like Wikipedia or police reports

references to authoritative sources or reports

No Comments

No Known Activations