INDEX

Explanations

expressions of reassurance or acceptance

oai_token-act-pair · gpt-3.5-turbo

expressions of acceptance or reassurance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

riber

-0.78

chet

-0.76

quin

-0.74

sten

-0.70

ulhu

-0.68

arcity

-0.67

Downloadha

-0.62

etheus

-0.61

omics

-0.60

rib

-0.60

POSITIVE LOGITS

AY

0.93

 okay

0.74

 alright

0.72

 anymore

0.68

ol

0.68

tta

0.66

atically

0.64

enough

0.64

 enough

0.64

ãģĨ

0.62

Activations Density 0.059%

expressions of reassurance or acceptance

expressions of acceptance or reassurance

No Comments

No Known Activations