INDEX

Explanations

specific names or terms related to individuals in various contexts

oai_token-act-pair · gpt-3.5-turbo

names of individuals, particularly those repeated multiple times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Genesis

-0.66

 Tune

-0.64

 Sailor

-0.64

 Survivors

-0.61

 sperm

-0.61

 Cosmic

-0.61

 Mercury

-0.60

 Scouting

-0.60

 sterile

-0.60

 gearing

-0.59

POSITIVE LOGITS

opol

1.06

oras

1.04

atche

1.02

ajo

1.00

rast

1.00

entin

0.95

onite

0.95

chen

0.94

orian

0.94

uers

0.94

Activations Density 0.047%

specific names or terms related to individuals in various contexts

names of individuals, particularly those repeated multiple times

No Comments

No Known Activations