INDEX

Explanations

phrases related to taking action or making decisions

oai_token-act-pair · gpt-3.5-turbo

references to actions taken or proposed 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

conservancy

-0.83

 arsen

-0.67

 abund

-0.67

iciency

-0.64

population

-0.63

 possessions

-0.62

paralle

-0.62

 veiled

-0.62

 abundant

-0.61

 ancest

-0.61

POSITIVE LOGITS

iveness

0.90

ional

0.89

 action

0.86

ality

0.85

 Replay

0.84

ivism

0.83

naire

0.82

uations

0.81

ulatory

0.79

igraph

0.79

Activations Density 0.031%

phrases related to taking action or making decisions

references to actions taken or proposed in various contexts

No Comments

No Known Activations