INDEX

Explanations

words related to making appeals or requests for action

oai_token-act-pair · gpt-3.5-turbo

instances of the word "called" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bilt

-0.83

bourne

-0.73

inth

-0.71

âĢ¢âĢ¢âĢ¢âĢ¢

-0.68

âĢ¢âĢ¢

-0.67

cffff

-0.66

omore

-0.65

olitics

-0.64

 unden

-0.63

 istg

-0.62

POSITIVE LOGITS

0.85

igraph

0.83

phas

0.82

calling

0.81

 calling

0.79

 bluff

0.78

 Calling

0.76

call

0.76

 forth

0.76

 Call

0.74

Activations Density 0.060%

words related to making appeals or requests for action

instances of the word "called" in various contexts

No Comments

No Known Activations