INDEX

Explanations

words related to the term "Tro" with varying activations indicating differing degrees of relevance or importance

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Tro" 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

ividual

-0.74

UAL

-0.66

icago

-0.65

à¼

-0.65

-0.60

ãĤ¦ãĤ¹

-0.60

soever

-0.60

,,,,

-0.59

IST

-0.59

ually

-0.58

POSITIVE LOGITS

phies

1.06

opers

1.04

dden

1.04

opa

1.00

kefeller

1.00

Tro

0.90

ppo

0.90

tro

0.88

phy

0.88

oby

0.86

Activations Density 0.015%

words related to the term "Tro" with varying activations indicating differing degrees of relevance or importance

occurrences of the word "Tro" in various contexts

No Comments

No Known Activations