INDEX

Explanations

historical terms or references

oai_token-act-pair · gpt-3.5-turbo

references to historical figures or the term "historian."

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

 Leilan

-0.74

ateral

-0.68

PLIED

-0.66

 downhill

-0.64

BOX

-0.63

[];

-0.63

backer

-0.63

Tube

-0.62

CLASSIFIED

-0.62

 learning

-0.62

POSITIVE LOGITS

orically

1.51

orical

1.50

oric

1.27

orians

1.27

orian

1.19

ogram

1.09

idine

1.05

alog

1.04

adr

1.03

orie

1.03

Activations Density 0.013%

historical terms or references

references to historical figures or the term "historian."

No Comments

No Known Activations