INDEX

Explanations

instances of the word "it" followed by descriptive or potentially evaluative adjectives or expressions

oai_token-act-pair · gpt-3.5-turbo

instances of uncertainty or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ãģ®éŃĶ

-0.71

licts

-0.64

ibel

-0.62

 GEAR

-0.62

aii

-0.62

lict

-0.61

icals

-0.59

ocaust

-0.59

ament

-0.58

ĸļ

-0.58

POSITIVE LOGITS

 someday

0.99

 misunder

0.95

 somew

0.91

 underest

0.84

 underestimated

0.84

 subconscious

0.81

 wiser

0.77

 underrated

0.77

 sensing

0.75

 coincidence

0.74

Activations Density 0.280%

instances of the word "it" followed by descriptive or potentially evaluative adjectives or expressions

instances of uncertainty or speculation

No Comments

No Known Activations