INDEX

Explanations

conjunctions and transitional phrases

oai_token-act-pair · gpt-3.5-turbo

transitional and contrasting phrases

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 realise

-0.62

"},"

-0.53

ggles

-0.53

Firstly

-0.53

 ageing

-0.53

 recognise

-0.53

 Personally

-0.52

cients

-0.52

Anyway

-0.52

 Suppose

-0.51

POSITIVE LOGITS

0.94

.,

0.71

,...

0.66

,.

0.64

 officials

0.61

 investigators

0.58

 deputies

0.58

!,

0.57

,,

0.55

terday

0.55

Activations Density 0.337%

conjunctions and transitional phrases

transitional and contrasting phrases

No Known Activations