INDEX

Explanations

phrases indicating a central or important location

oai_token-act-pair · gpt-3.5-turbo

constructs that indicate possession or relationship

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

externalActionCode

-0.84

notations

-0.73

fn

-0.72

than

-0.69

zbollah

-0.69

claim

-0.66

marg

-0.64

bro

-0.63

.''.

-0.61

>(

-0.60

POSITIVE LOGITS

liest

0.92

 sorts

0.85

undown

0.72

 Mecca

0.65

 Clair

0.64

olls

0.63

amina

0.63

 heaven

0.62

agonist

0.60

hest

0.60

Activations Density 0.167%

phrases indicating a central or important location

constructs that indicate possession or relationship

No Comments

No Known Activations