INDEX

Explanations

specific times and dates in a structured format

oai_token-act-pair · gpt-3.5-turbo

specific days and times mentioned in the text

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

Ĥª

-0.68

 shrunk

-0.66

rul

-0.65

 weakened

-0.65

 subclass

-0.63

 collaborations

-0.62

 cloning

-0.62

 disbanded

-0.61

 emulation

-0.61

 taste

-0.60

POSITIVE LOGITS

 Doors

0.82

PST

0.82

CST

0.80

EST

0.78

EST

0.76

PDT

0.74

 curfew

0.70

 Kills

0.68

 Recre

0.68

GMT

0.66

Activations Density 0.191%

specific times and dates in a structured format

specific days and times mentioned in the text

No Comments

No Known Activations