INDEX

Explanations

words related to the name "Rogers"

oai_token-act-pair · gpt-3.5-turbo

the name "Rogers" 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

spring

-0.71

âĢ¢âĢ¢âĢ¢âĢ¢

-0.70

emort

-0.69

itia

-0.68

visory

-0.68

fare

-0.67

oard

-0.66

spread

-0.65

fix

-0.65

pron

-0.65

POSITIVE LOGITS

loo

1.07

 Rogers

1.03

burgh

0.90

tel

0.87

Tel

0.83

hiba

0.80

dale

0.79

sonian

0.75

ratulations

0.75

otiation

0.75

Activations Density 0.012%

words related to the name "Rogers"

the name "Rogers" in various contexts

No Comments

No Known Activations