INDEX

Explanations

references to academic institutions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "M"

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

 tipped

-0.77

 begg

-0.69

ãĤ¡

-0.66

 bruised

-0.63

 yours

-0.62

 centre

-0.60

 strained

-0.60

Nep

-0.59

 soup

-0.59

tip

-0.58

POSITIVE LOGITS

useum

1.15

asonic

1.11

otive

1.10

insk

1.07

ISSION

1.05

ONEY

1.05

ountain

1.04

asters

1.03

umbai

1.01

igration

1.01

Activations Density 0.054%

references to academic institutions

occurrences of the letter "M"

No Comments

No Known Activations