INDEX

Explanations

specific identifiers and numerical values associated with data in a structured format

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

 attm

-0.70

ó

-0.70

 reconc

-0.67

ictional

-0.67

sonian

-0.62

ologically

-0.62

lightly

-0.61

minist

-0.61

 compliments

-0.60

POSITIVE LOGITS

\":

0.69

 Droid

0.67

oise

0.65

rador

0.65

 Haste

0.65

 Shuttle

0.63

 Atlantis

0.62

 Tile

0.62

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

0.61

 Ogre

0.61

Activations Density 0.498%

specific identifiers and numerical values associated with data in a structured format

No Comments

No Known Activations