INDEX

Explanations

phrases that indicate summaries or overviews of content

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

alties

-0.87

aneers

-0.76

esm

-0.74

hes

-0.73

xit

-0.72

bons

-0.69

ãĥĺ

-0.69

cair

-0.69

culosis

-0.67

bah

-0.66

POSITIVE LOGITS

 example

0.94

 reminder

0.77

 illustration

0.76

 examples

0.76

 rundown

0.75

 quick

0.74

 excerpt

0.74

 primer

0.72

 testim

0.72

 preview

0.71

Activations Density 0.152%

phrases that indicate summaries or overviews of content

No Comments

No Known Activations