INDEX

Explanations

phrases indicating a requirement or necessity

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate necessity or requirement

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

 Tide

-0.77

sight

-0.74

 Tate

-0.71

ight

-0.68

 Rapp

-0.67

luaj

-0.66

Tow

-0.65

 Kers

-0.65

 Kind

-0.64

Mem

-0.64

POSITIVE LOGITS

require

1.04

encies

0.96

MENTS

0.91

requires

0.86

 require

0.85

 confir

0.85

enance

0.85

 requiring

0.78

 requires

0.78

LESS

0.77

Activations Density 0.019%

phrases indicating a requirement or necessity

phrases that indicate necessity or requirement

No Comments

No Known Activations