INDEX

Explanations

keywords related to membership and participation in different contexts and scenarios

oai_token-act-pair · gpt-3.5-turbo

terms related to membership and participation

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

Dispatch

-0.80

geries

-0.77

rup

-0.69

ropolis

-0.68

pex

-0.67

sel

-0.67

geon

-0.64

ospital

-0.64

leys

-0.64

awar

-0.63

POSITIVE LOGITS

 dues

0.98

 rates

0.88

 rate

0.84

 oath

0.83

 fees

0.82

fee

0.78

 patterns

0.76

 Rates

0.76

 Requirements

0.75

 rolls

0.75

Activations Density 0.144%

keywords related to membership and participation in different contexts and scenarios

terms related to membership and participation

No Comments

No Known Activations