INDEX

Explanations

names related to different individuals

oai_token-act-pair · gpt-3.5-turbo

names of individuals or references to people

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icating

-1.04

icate

-0.90

ishing

-0.88

eral

-0.86

rican

-0.86

ications

-0.85

icated

-0.85

ishment

-0.84

igating

-0.84

ICAN

-0.84

POSITIVE LOGITS

bone

0.82

ģ«

0.72

ãĤ¼ãĤ¦ãĤ¹

0.69

paio

0.69

 mathemat

0.66

âĸ¬

0.65

mie

0.64

 Christensen

0.64

 Schmidt

0.64

 unfocusedRange

0.62

Activations Density 0.058%

names related to different individuals

names of individuals or references to people

No Comments

No Known Activations