INDEX

Explanations

mentions of reputation, especially when associated with positive or negative connotations

oai_token-act-pair · gpt-3.5-turbo

references to reputation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cise

-0.81

tein

-0.78

pheus

-0.75

vention

-0.73

early

-0.71

nes

-0.70

stad

-0.69

onal

-0.68

wed

-0.66

isting

-0.66

POSITIVE LOGITS

 reputation

0.97

 tarn

0.90

 internationally

0.85

 tremend

0.84

 bearer

0.83

 veter

0.81

 globally

0.73

 sterling

0.71

 nationally

0.67

©¶æ¥µ

0.67

Activations Density 0.045%

mentions of reputation, especially when associated with positive or negative connotations

references to reputation

No Comments

No Known Activations