INDEX

Explanations

phrases referring to requirements or conditions for something to happen

oai_token-act-pair · gpt-3.5-turbo

the infinitive form of verbs following the word "to."

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

 newsp

-0.69

Flo

-0.64

typ

-0.59

 Oops

-0.58

rising

-0.57

 Caller

-0.57

quickShipAvailable

-0.56

 Supervisor

-0.55

pants

-0.54

 corridors

-0.54

POSITIVE LOGITS

 emulate

1.02

 take

0.97

be

0.93

 keep

0.89

 claim

0.89

iling

0.87

 avoid

0.86

 participate

0.86

 prove

0.86

 reach

0.86

Activations Density 0.101%

phrases referring to requirements or conditions for something to happen

the infinitive form of verbs following the word "to."

No Comments

No Known Activations