INDEX

Explanations

specific numerical values, especially related to identifiers or data points in a dataset

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res_post_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_6.pt

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

neys

-0.69

istry

-0.63

 peninsula

-0.63

sterdam

-0.63

 disguise

-0.61

 prem

-0.60

 realism

-0.59

amount

-0.59

 whis

-0.59

 conductor

-0.58

POSITIVE LOGITS

.............

0.80

ãĥı

0.77

milo

0.77

eus

0.74

ulz

0.74

00000000

0.73

DragonMagazine

0.71

classified

0.71

Activations Density 0.100%

specific numerical values, especially related to identifiers or data points in a dataset

No Comments

No Known Activations