INDEX

Explanations

information related to numerical quantities or statistics

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate approximate quantities or statistics

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

agate

-0.75

idia

-0.65

heses

-0.65

dll

-0.62

 Definition

-0.61

 Solution

-0.60

 protector

-0.60

 proclamation

-0.60

 Creator

-0.59

":["

-0.59

POSITIVE LOGITS

undreds

0.93

 dozen

0.86

0.80

0.79

0.78

0.77

 fewer

0.75

 tonnes

0.75

Activations Density 0.160%

information related to numerical quantities or statistics

phrases that indicate approximate quantities or statistics

No Comments

No Known Activations