INDEX

Explanations

verbs or phrases related to reaching a resolution or agreement

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "settle" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eway

-0.91

otic

-0.77

 Canaveral

-0.77

icipated

-0.76

emic

-0.73

saf

-0.70

emonic

-0.68

ery

-0.66

inx

-0.65

 Mansion

-0.61

POSITIVE LOGITS

 down

0.84

 settle

0.83

hiro

0.81

 disputes

0.80

 settles

0.78

 settling

0.78

 ashore

0.77

 grievances

0.77

itating

0.75

itate

0.74

Activations Density 0.027%

verbs or phrases related to reaching a resolution or agreement

occurrences of the word "settle" and its variations

No Comments

No Known Activations