INDEX

Explanations

places or locations indicated by the word "there"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "there"

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

 Abyss

-0.64

 Doctors

-0.64

BIP

-0.63

 Dresden

-0.62

 Observer

-0.61

 Lancet

-0.60

 Towns

-0.60

itialized

-0.59

 Compliance

-0.59

ONSORED

-0.59

POSITIVE LOGITS

abouts

1.13

tics

0.91

tical

0.91

tic

0.77

upon

0.72

comings

0.72

roxy

0.70

geist

0.69

ackets

0.68

agon

0.67

Activations Density 0.037%

places or locations indicated by the word "there"

occurrences of the word "there"

No Comments

No Known Activations