INDEX

Explanations

terms related to physical and metaphorical resistance

oai_token-act-pair · gpt-3.5-turbo

phrases that discuss resistance in various contexts, particularly in a metaphorical or social sense

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ghazi

-0.96

ewater

-0.76

oba

-0.72

osta

-0.70

=-=-=-=-

-0.70

estone

-0.69

owler

-0.69

uliffe

-0.68

orah

-0.68

istical

-0.67

POSITIVE LOGITS

 thereto

0.85

bands

0.76

 fighters

0.75

mount

0.73

 resistant

0.72

 resistance

0.71

 inhibitor

0.69

ENCE

0.68

 against

0.67

 tiss

0.66

Activations Density 0.028%

terms related to physical and metaphorical resistance

phrases that discuss resistance in various contexts, particularly in a metaphorical or social sense

No Comments

No Known Activations