INDEX

Explanations

phrases related to conflicts of interest

oai_token-act-pair · gpt-3.5-turbo

references to conflicts, particularly in legal or governance contexts

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

GC

-0.74

vation

-0.73

alty

-0.72

DT

-0.69

ulously

-0.68

************

-0.66

GV

-0.66

sonian

-0.66

erd

-0.65

icrobial

-0.65

POSITIVE LOGITS

 raging

0.84

 between

0.81

ual

0.78

 unresolved

0.77

 Royale

0.75

 situations

0.75

 resolution

0.74

uous

0.74

 arises

0.74

 conflicts

0.73

Activations Density 0.034%

phrases related to conflicts of interest

references to conflicts, particularly in legal or governance contexts

No Comments

No Known Activations