INDEX

Explanations

years mentioned as dates

oai_token-act-pair · gpt-3.5-turbo

occurrences of the year 1984

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 lawy

-0.70

hop

-0.70

edge

-0.69

 deliber

-0.64

actions

-0.64

 periphery

-0.63

hed

-0.63

 craft

-0.62

uden

-0.61

 limb

-0.60

POSITIVE LOGITS

 ï¿½ï¿½ï¿½ï¿½

0.82

å¹

0.77

ixties

0.77

$$$$

0.72

 Schwarzenegger

0.72

ãĥ¼

0.71

ãĤ¦ãĤ¹

0.70

-'

0.69

regate

0.69

ICT

0.69

Activations Density 0.020%

years mentioned as dates

occurrences of the year 1984

No Comments

No Known Activations