INDEX

Explanations

names of specific locations or places, including cities and specific company names

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "G" in various contexts

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

terday

-0.72

ĸļ

-0.70

htt

-0.62

 craw

-0.62

oÄŁ

-0.62

 Conquest

-0.61

vou

-0.61

 retrospect

-0.60

 sight

-0.60

 Ruins

-0.60

POSITIVE LOGITS

asp

1.15

ossip

1.10

irlfriend

1.10

oliath

1.10

iant

1.08

reetings

1.06

CHQ

1.06

ospels

1.06

reet

1.05

ather

1.05

Activations Density 0.048%

names of specific locations or places, including cities and specific company names

occurrences of the letter "G" in various contexts

No Comments

No Known Activations