INDEX

Explanations

phrases related to making comparisons between different groups or entities

oai_token-act-pair · gpt-3.5-turbo

quantitative comparisons and statistics regarding various groups and conditions

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

Reviewer

-0.84

ointed

-0.61

orum

-0.61

minist

-0.61

 furthermore

-0.61

isson

-0.60

ornia

-0.58

 besides

-0.58

 Loren

-0.57

 thanked

-0.57

POSITIVE LOGITS

 counterparts

0.89

 previous

0.75

 existing

0.75

 realities

0.75

 conceptions

0.73

²¾

0.71

 actual

0.70

 predecessors

0.67

typ

0.67

ahime

0.66

Activations Density 0.348%

phrases related to making comparisons between different groups or entities

quantitative comparisons and statistics regarding various groups and conditions

No Comments

No Known Activations