INDEX

Explanations

descriptions of specific activities or steps in a process

oai_token-act-pair · gpt-3.5-turbo

references to awards and accomplishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

FAA

-0.59

Defense

-0.58

Sanders

-0.57

ENSE

-0.57

ATF

-0.57

bernatorial

-0.57

defense

-0.56

 informational

-0.55

 utilize

-0.55

 Coliseum

-0.54

POSITIVE LOGITS

 paed

0.90

 Â£

0.81

 maths

0.80

 mould

0.77

 learnt

0.77

 organised

0.75

jew

0.74

 pract

0.71

 behavioural

0.71

 Belfast

0.70

Activations Density 2.342%

descriptions of specific activities or steps in a process

references to awards and accomplishments

No Comments

No Known Activations