INDEX

Explanations

words related to addition or totals

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "sum" in relation to calculations or aggregations

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

 Defenders

-0.70

 Kers

-0.69

 livest

-0.69

 Ferry

-0.68

 surn

-0.68

 Flame

-0.62

eele

-0.59

 foreclosure

-0.59

 Blitz

-0.58

 Battles

-0.57

POSITIVE LOGITS

ming

1.44

mers

1.11

mits

1.09

ulative

0.92

otaur

0.91

sum

0.89

sum

0.86

total

0.81

mes

0.81

iture

0.80

Activations Density 0.014%

words related to addition or totals

occurrences of the word "sum" in relation to calculations or aggregations

No Comments

No Known Activations