INDEX

Explanations

instances of the word "that"

oai_token-act-pair · gpt-3.5-turbo

phrases that use "in that" to introduce explanations or clarifications

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

ormons

-0.71

Guard

-0.68

onto

-0.66

rior

-0.66

asters

-0.64

 srfAttach

-0.63

 Leilan

-0.63

quit

-0.60

inx

-0.60

aciously

-0.59

POSITIVE LOGITS

 vein

0.96

 regard

0.95

 vicinity

0.90

 particular

0.89

 same

0.89

 fateful

0.82

 manner

0.80

 area

0.78

 circumstance

0.78

 direction

0.77

Activations Density 0.038%

instances of the word "that"

phrases that use "in that" to introduce explanations or clarifications

No Comments

No Known Activations