INDEX

Explanations

keywords related to tasks or actions that require assistance or guidance

oai_token-act-pair · gpt-3.5-turbo

phrases that express necessity or requirement

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

 Democr

-0.76

cow

-0.62

 Brewers

-0.61

pee

-0.60

 Pill

-0.59

ihu

-0.58

 Sturgeon

-0.58

Bad

-0.57

cession

-0.57

cheat

-0.57

POSITIVE LOGITS

lessly

1.25

ache

0.88

igslist

0.72

aches

0.70

0.68

LES

0.68

 assistance

0.67

ancies

0.67

nces

0.64

 sust

0.64

Activations Density 0.062%

keywords related to tasks or actions that require assistance or guidance

phrases that express necessity or requirement

No Comments

No Known Activations