INDEX

Explanations

comparative adjectives expressing difficulty

oai_token-act-pair · gpt-3.5-turbo

references to difficulty or challenges

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

Kings

-0.72

enture

-0.72

endar

-0.71

itas

-0.69

atern

-0.68

 Lights

-0.66

ificantly

-0.65

erity

-0.65

mosp

-0.64

ript

-0.64

POSITIVE LOGITS

coded

0.79

 punishable

0.79

 punished

0.77

 forgiving

0.75

ACH

0.72

 harder

0.71

 slog

0.69

wired

0.68

 hitters

0.67

 prosecuted

0.67

Activations Density 0.051%

comparative adjectives expressing difficulty

references to difficulty or challenges

No Comments

No Known Activations