INDEX

Explanations

words related to physical locations or movements

oai_token-act-pair · gpt-3.5-turbo

mentions of physical locations or specific entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

MSN

-0.69

lez

-0.65

itri

-0.63

iversal

-0.61

etheless

-0.60

iannopoulos

-0.59

=-=-=-=-

-0.57

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.56

GST

-0.55

ailability

-0.55

POSITIVE LOGITS

 Rockefeller

0.59

 Gemini

0.51

 Dickinson

0.51

 Plum

0.50

 Shap

0.49

ows

0.49

 rook

0.49

ivist

0.48

 prestige

0.48

 Bone

0.47

Activations Density 1.771%

words related to physical locations or movements

mentions of physical locations or specific entities

No Comments

No Known Activations