INDEX

Explanations

words related to legal actions, specifically regarding being remanded or reprimanded

oai_token-act-pair · gpt-3.5-turbo

passive voice constructions, specifically the use of "remanded" and its variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

saf

-0.73

INESS

-0.73

Article

-0.67

etta

-0.65

liest

-0.63

ched

-0.62

Chance

-0.61

pei

-0.61

è»

-0.61

ãĥ¼ãĥ«

-0.61

POSITIVE LOGITS

anded

1.58

anding

1.53

ĸļ

0.89

ragon

0.88

ands

0.84

english

0.84

arity

0.79

ishly

0.78

lass

0.78

iple

0.77

Activations Density 0.010%

words related to legal actions, specifically regarding being remanded or reprimanded

passive voice constructions, specifically the use of "remanded" and its variations

No Comments

No Known Activations