INDEX

Explanations

words related to certainty and likelihood

oai_token-act-pair · gpt-3.5-turbo

sentences that convey certainty or factual statements

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

 bunch

-0.74

 IMAGES

-0.66

ukong

-0.65

 scrimmage

-0.63

VIP

-0.62

 carc

-0.61

luaj

-0.61

 Seah

-0.61

 Telesc

-0.61

 scoreboard

-0.60

POSITIVE LOGITS

 unclear

1.14

 unlikely

0.86

 clear

0.86

 conceivable

0.83

govtrack

0.82

oen

0.82

 doubtful

0.81

 inevitable

0.81

 imperative

0.79

 impossible

0.79

Activations Density 0.330%

words related to certainty and likelihood

sentences that convey certainty or factual statements

No Comments

No Known Activations