INDEX

Explanations

words related to measurement or comparison

oai_token-act-pair · gpt-3.5-turbo

terms related to foundational elements or baseline parameters in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acles

-0.70

omer

-0.69

Compat

-0.69

uild

-0.68

phan

-0.67

oping

-0.67

ularity

-0.66

oth

-0.66

dfx

-0.64

 Stall

-0.64

POSITIVE LOGITS

 baseline

0.90

 outline

0.78

 sidx

0.76

gradient

0.74

 jumper

0.72

tenance

0.72

phrine

0.70

 measures

0.67

 dummy

0.65

 measurement

0.65

Activations Density 0.006%

words related to measurement or comparison

terms related to foundational elements or baseline parameters in various contexts

No Comments

No Known Activations