INDEX

Explanations

words related to specific names, entities, and titles

oai_token-act-pair · gpt-3.5-turbo

names related to notable individuals or events

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

Uncommon

-0.72

yright

-0.69

cot

-0.67

atform

-0.62

leneck

-0.61

FG

-0.60

 Engels

-0.59

 surpr

-0.58

etheus

-0.57

Brave

-0.57

POSITIVE LOGITS

pta

0.92

oslav

0.78

onica

0.73

utsche

0.73

amiya

0.70

iae

0.68

onduct

0.67

gaard

0.66

cheat

0.65

letal

0.64

Activations Density 0.580%

words related to specific names, entities, and titles

names related to notable individuals or events

No Comments

No Known Activations