INDEX

Explanations

phrases indicating a comparison or consequence

oai_token-act-pair · gpt-3.5-turbo

conditional phrases or clauses that elaborate or specify a situation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

athi

-0.69

Behind

-0.63

holding

-0.61

 Dial

-0.61

MENTS

-0.61

Queen

-0.60

da

-0.59

Bas

-0.58

BLE

-0.58

STE

-0.58

POSITIVE LOGITS

 resulted

0.98

 translates

0.95

 admittedly

0.94

 prompts

0.89

 explains

0.89

 brings

0.88

 incidentally

0.88

 begs

0.88

 culminated

0.87

 leads

0.86

Activations Density 0.120%

phrases indicating a comparison or consequence

conditional phrases or clauses that elaborate or specify a situation

No Comments

No Known Activations