INDEX

Explanations

the word "Lloyd"

oai_token-act-pair · gpt-3.5-turbo

the presence of the term "Ll" related to a specific pharmacy group or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ãĥ¼ãĥĨ

-0.90

nels

-0.86

culosis

-0.84

ļéĨĴ

-0.82

ãĥį

-0.82

å§«

-0.81

rawdownloadcloneembedreportprint

-0.79

schild

-0.78

ãĥĹ

-0.76

REDACTED

-0.73

POSITIVE LOGITS

Ll

1.28

orld

0.96

ow

0.95

ll

0.91

uci

0.91

ording

0.89

argo

0.88

anca

0.86

owship

0.85

iffs

0.85

Activations Density 0.016%

the word "**Lloyd**"

the presence of the term "Ll" related to a specific pharmacy group or entity

No Comments

No Known Activations

the word "Lloyd"