INDEX

Explanations

numbers, quantities, and comparisons

oai_token-act-pair · gpt-3.5-turbo

negations or phrases indicating limitations or specificity

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

ussions

-0.82

lb

-0.62

 unsuccessfully

-0.62

acas

-0.61

rams

-0.61

ounces

-0.60

osures

-0.59

 Remain

-0.59

Disk

-0.59

 Alam

-0.57

POSITIVE LOGITS

soDeliveryDate

0.85

 gonna

0.79

iour

0.75

 funny

0.72

TY

0.70

 eyebrow

0.70

 kinda

0.69

 gotta

0.69

 ðŁĳ

0.69

ðŁ

0.69

Activations Density 0.319%

numbers, quantities, and comparisons

negations or phrases indicating limitations or specificity

No Comments

No Known Activations