INDEX

Explanations

keywords related to tolerance, intolerance, and acceptance

oai_token-act-pair · gpt-3.5-turbo

concepts and terms related to tolerance and intolerance

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Downloadha

-0.75

prints

-0.69

escription

-0.65

alyst

-0.64

dir

-0.63

 Overs

-0.62

 prest

-0.62

call

-0.61

 Indust

-0.61

rounder

-0.61

POSITIVE LOGITS

ances

0.90

ANC

0.87

 tolerant

0.85

ANCE

0.82

 intoler

0.80

 intolerance

0.77

 toler

0.77

ably

0.73

ance

0.72

ancing

0.71

Activations Density 0.083%

keywords related to tolerance, intolerance, and acceptance

concepts and terms related to tolerance and intolerance

No Comments

No Known Activations