INDEX

Explanations

contractions ending in "'t"

oai_token-act-pair · gpt-3.5-turbo

negations and expressions of disbelief or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Invisible

-0.61

è¦ļéĨĴ

-0.58

Bench

-0.57

oret

-0.56

 underway

-0.55

active

-0.54

\<

-0.54

near

-0.53

site

-0.53

API

-0.53

POSITIVE LOGITS

 hesitate

0.87

 tolerate

0.84

ĸļ

0.82

]}

0.77

quit

0.76

 necessarily

0.75

 classify

0.73

 recommend

0.73

 interfere

0.71

 dare

0.70

Activations Density 0.086%

contractions ending in "'t"

negations and expressions of disbelief or uncertainty

No Comments

No Known Activations