INDEX

Explanations

references to different views or perspectives

oai_token-act-pair · gpt-3.5-turbo

instances of the word "view" related to observations or activities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lull

-0.78

 breathing

-0.76

odic

-0.74

 downturn

-0.71

 instr

-0.69

 reorgan

-0.68

 escal

-0.67

 extingu

-0.66

 electr

-0.65

astically

-0.65

POSITIVE LOGITS

view

1.17

edIn

1.01

port

0.93

views

0.92

ership

0.87

Cache

0.86

PORT

0.84

finder

0.84

 Manor

0.84

er

0.83

Activations Density 0.013%

references to different views or perspectives

instances of the word "view" related to observations or activities in various contexts

No Comments

No Known Activations