INDEX

Explanations

words related to small scale and local contexts

oai_token-act-pair · gpt-3.5-turbo

references to small or independent entities, particularly businesses or organizations

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

Negative Logits

Ö¼

-0.92

ortmund

-0.73

 Aires

-0.68

Â¯

-0.68

 Gleaming

-0.68

orne

-0.68

cape

-0.67

orp

-0.67

ãĤ§

-0.67

ITION

-0.66

POSITIVE LOGITS

 insignificant

0.92

 harmless

0.82

 inexpensive

0.81

(<

0.81

 inefficient

0.79

ucket

0.79

 trickle

0.79

 incremental

0.79

medium

0.77

 manageable

0.75

Activations Density 0.327%

words related to small scale and local contexts

references to small or independent entities, particularly businesses or organizations

No Known Activations