INDEX

Explanations

occurrences of the word "was" in sentences

oai_token-act-pair · gpt-3.5-turbo

instances of the word "was" indicating past events or situations

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

entric

-0.76

ledge

-0.67

lev

-0.66

arta

-0.64

forward

-0.63

ledged

-0.63

objects

-0.62

aucus

-0.61

 chromosomes

-0.61

Make

-0.61

POSITIVE LOGITS

hes

0.96

wolves

0.93

wolf

0.91

 originally

0.89

 instrumental

0.82

hers

0.74

 cruc

0.73

 able

0.73

 born

0.72

 formerly

0.71

Activations Density 0.223%

occurrences of the word "was" in sentences

instances of the word "was" indicating past events or situations

No Comments

No Known Activations