INDEX

Explanations

specific phrases or terms related to official names or titles

oai_token-act-pair · gpt-3.5-turbo

repeated mention of the word "the" 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

earances

-0.69

 suppose

-0.69

 bapt

-0.68

 furthermore

-0.66

SPONSORED

-0.65

ensibly

-0.64

istries

-0.63

uality

-0.63

aciously

-0.63

leeve

-0.62

POSITIVE LOGITS

 largest

0.76

 proverbial

0.75

Street

0.75

 aforementioned

0.75

sis

0.73

ocratic

0.73

interstitial

0.72

atre

0.71

 dreaded

0.69

Bron

0.69

Activations Density 0.184%

specific phrases or terms related to official names or titles

repeated mention of the word "the" in various contexts

No Comments

No Known Activations