INDEX

Explanations

terms related to reaching agreements or settlements

oai_token-act-pair · gpt-3.5-turbo

instances of the word "compromise" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ahon

-0.85

vals

-0.74

asters

-0.72

aur

-0.71

odes

-0.71

umin

-0.71

soon

-0.68

aver

-0.67

uf

-0.67

lining

-0.67

POSITIVE LOGITS

 compromise

1.16

 compromises

1.11

romising

0.84

EngineDebug

0.82

 compromising

0.81

 comprom

0.77

 negotiator

0.75

smanship

0.74

 shenan

0.73

 negotiators

0.72

Activations Density 0.009%

terms related to reaching agreements or settlements

instances of the word "compromise" and its variations

No Comments

No Known Activations