INDEX

Explanations

terms related to actions or decisions being taken

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the" indicating a common theme or focus in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ndra

-0.85

ambo

-0.78

Ü

-0.76

nell

-0.72

tions

-0.70

ailability

-0.70

Animation

-0.67

etheless

-0.65

ONSORED

-0.64

ntil

-0.63

POSITIVE LOGITS

 seriously

0.96

 plunge

0.83

 lightly

0.82

 aback

0.79

cue

0.77

 reins

0.76

 stride

0.75

 away

0.74

 cues

0.74

 cogn

0.73

Activations Density 0.223%

terms related to actions or decisions being taken

instances of the word "the" indicating a common theme or focus in the text

No Comments

No Known Activations