INDEX

Explanations

mentions of specific locations along with names or descriptions of people

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals and their associated details

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

 potentially

-0.74

 initially

-0.68

 unexpectedly

-0.66

 seemingly

-0.65

 ostensibly

-0.64

 buildup

-0.62

 mechanically

-0.62

 historically

-0.62

 preempt

-0.61

 traditionally

-0.61

POSITIVE LOGITS

$$$$

0.83

ttp

0.78

 Reply

0.78

(@

0.78

imeo

0.77

STAR

0.75

Site

0.75

0.74

HQ

0.74

Activations Density 0.579%

mentions of specific locations along with names or descriptions of people

references to specific individuals and their associated details

No Comments

No Known Activations