INDEX

Explanations

phrases related to comparison or contrast between different groups or situations

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce topics or issues

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

oris

-0.86

vier

-0.75

sav

-0.74

ertodd

-0.71

cos

-0.71

contract

-0.70

imon

-0.70

raid

-0.69

hematic

-0.67

wine

-0.67

POSITIVE LOGITS

 raining

0.72

 pouring

0.67

 roaring

0.66

 downhill

0.66

 squarely

0.64

 alive

0.64

 undone

0.61

 knocking

0.61

 apart

0.61

 adversity

0.61

Activations Density 0.032%

phrases related to comparison or contrast between different groups or situations

phrases that introduce topics or issues

No Comments

No Known Activations