INDEX

Explanations

phrases expressing plans or intentions

oai_token-act-pair · gpt-3.5-turbo

modal verbs expressing intention or future actions

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

artney

-0.82

rawler

-0.68

Args

-0.68

VERTISEMENT

-0.68

 respectively

-0.61

-+-+

-0.60

eele

-0.60

bies

-0.60

ritional

-0.60

 guiActiveUnfocused

-0.59

POSITIVE LOGITS

 fortunate

0.83

 personally

0.79

 myself

0.76

lene

0.76

stic

0.72

 gladly

0.72

opic

0.70

lah

0.70

 kidding

0.69

 honored

0.69

Activations Density 0.325%

phrases expressing plans or intentions

modal verbs expressing intention or future actions

No Comments

No Known Activations