INDEX

Explanations

past tense verbs indicating a change in state or action

oai_token-act-pair · gpt-3.5-turbo

past tense verbs indicating actions or changes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

adj

-0.75

hart

-0.65

Ranked

-0.62

ofi

-0.61

esp

-0.61

ns

-0.60

hl

-0.59

States

-0.58

abet

-0.57

POSITIVE LOGITS

 hitherto

0.76

 undermin

0.70

 lately

0.70

 since

0.69

 sufficiently

0.68

 millenn

0.67

 countless

0.67

CLASSIFIED

0.65

Quantity

0.64

iless

0.63

Activations Density 0.446%

past tense verbs indicating a change in state or action

past tense verbs indicating actions or changes

No Comments

No Known Activations