INDEX

Explanations

abbreviations that likely relate to official documents or organizations

oai_token-act-pair · gpt-3.5-turbo

references to organizational or corporate structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

lets

-0.68

 fortunate

-0.66

pring

-0.64

watch

-0.63

metadata

-0.62

!--

-0.61

osc

-0.58

bour

-0.57

idem

-0.57

 unlucky

-0.57

POSITIVE LOGITS

0.84

0.80

0.76

0.75

Ds

0.75

0.72

senal

0.72

Ts

0.70

Activations Density 0.060%

abbreviations that likely relate to official documents or organizations

references to organizational or corporate structures

No Comments

No Known Activations