INDEX

Explanations

phrases related to specific groups or entities within a larger context

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or groups within a societal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ILA

-0.71

BIL

-0.71

ess

-0.69

anan

-0.67

RES

-0.66

Lua

-0.64

eenth

-0.61

 trademarks

-0.61

Whereas

-0.61

stant

-0.60

POSITIVE LOGITS

 vicinity

1.38

 midst

0.99

 audience

0.97

 room

0.92

 periphery

0.88

 area

0.87

 region

0.85

 fray

0.85

 neighbourhood

0.84

 valley

0.80

Activations Density 0.203%

phrases related to specific groups or entities within a larger context

references to specific locations or groups within a societal context

No Comments

No Known Activations