INDEX

Explanations

pronouns followed by verbs indicating knowledge or perception

oai_token-act-pair · gpt-3.5-turbo

pronouns indicating relationships and connections between individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Spur

-0.72

vine

-0.71

heny

-0.65

 Surge

-0.64

 Dimensions

-0.64

 Definitions

-0.60

 Proced

-0.59

 Illustrated

-0.59

 itch

-0.59

 steroids

-0.58

POSITIVE LOGITS

sembly

0.86

mble

0.82

igl

0.74

self

0.74

cius

0.73

azi

0.71

ega

0.69

 condem

0.68

ngth

0.68

chwitz

0.68

Activations Density 0.254%

pronouns followed by verbs indicating knowledge or perception

pronouns indicating relationships and connections between individuals

No Comments

No Known Activations