INDEX

Explanations

phrases related to actions taken or decisions made by notable entities

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate actions or characteristics related to conflict or noteworthy events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

atin

-0.65

lex

-0.64

,,,,

-0.63

ctions

-0.63

nis

-0.62

dds

-0.61

cb

-0.61

acs

-0.60

.;

-0.60

.",

-0.60

POSITIVE LOGITS

 incidentally

0.92

 respectively

0.73

 admittedly

0.70

 prominently

0.70

 unsuccessfully

0.68

 ironically

0.65

 presumably

0.62

ulo

0.62

 essentially

0.62

 famously

0.61

Activations Density 0.391%

phrases related to actions taken or decisions made by notable entities

phrases that indicate actions or characteristics related to conflict or noteworthy events

No Comments

No Known Activations