INDEX

Explanations

text related to calls for or instances of taking action

oai_token-act-pair · gpt-3.5-turbo

references to taking action 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.76

iciency

-0.67

 abund

-0.67

 porous

-0.65

 Province

-0.64

Fey

-0.63

ringe

-0.63

oded

-0.60

oiler

-0.59

 illusions

-0.59

POSITIVE LOGITS

ional

0.92

 against

0.85

iveness

0.83

igraph

0.81

ivism

0.80

uations

0.79

naires

0.79

 ACTIONS

0.78

 action

0.78

aries

0.77

Activations Density 0.032%

text related to calls for or instances of taking action

references to taking action in various contexts

No Comments

No Known Activations