INDEX

Explanations

phrases indicating a certain type of emphasis or focus, typically highlighting a specific quality or characteristic

oai_token-act-pair · gpt-3.5-turbo

phrases expressing uncertainty or a sense of vagueness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

VEL

-0.66

OPE

-0.66

 Expansion

-0.64

VM

-0.62

 Examination

-0.61

ULT

-0.60

PT

-0.59

Ultra

-0.58

idate

-0.57

ODE

-0.57

POSITIVE LOGITS

entimes

0.89

nered

0.88

ling

0.79

heartedly

0.77

erd

0.75

hearted

0.75

cast

0.74

led

0.74

lier

0.74

entially

0.71

Activations Density 0.037%

phrases indicating a certain type of emphasis or focus, typically highlighting a specific quality or characteristic

phrases expressing uncertainty or a sense of vagueness

No Comments

No Known Activations