INDEX

Explanations

occurrences of possessive nouns or proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 's' in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Lauder

-0.74

 Sources

-0.69

RN

-0.65

 Nigel

-0.64

 Tours

-0.62

KH

-0.62

 Continental

-0.62

Sev

-0.61

KT

-0.61

 Alexandria

-0.61

POSITIVE LOGITS

uddenly

1.05

lightly

1.04

atisf

0.96

omew

0.93

pecially

0.93

ustainable

0.91

ifted

0.89

leeve

0.88

ensibly

0.88

ufficient

0.87

Activations Density 0.150%

occurrences of possessive nouns or proper nouns

occurrences of the letter 's' in a context

No Comments

No Known Activations